Method and device for intelligently identifying large deformation grade of soft rock tunnel based on monitoring data

Abstract

The invention discloses the technical field of soft rock deformation grade identification, and particularly discloses a method and a device for intelligently identifying the large deformation grade of a soft rock tunnel based on monitoring data. In the identification process of tunnel soft rock deformation, a tunnel to be detected is divided into a plurality of intervals to be detected in a segmentation mode, then a tunnel change model is constructed, and the large deformation grade of the tunnel to be detected is identified. The large deformation grade is identified by means of the difference value between the models, the identification efficiency is improved compared with existing manual identification, accurate identification can be achieved on deformation data in continuous monitoring time periods, the risk avoidance capacity is effectively improved, and the method is suitable for large-scale popularization and application. And the problem of complex soft rock tunnel deformation grade judgment in the existing deformation judgment is also solved.

Description

Technical Field

[0001] The present invention relates to the technical field of soft rock deformation level identification, and in particular to a method and a device for intelligently identifying the large deformation level of a soft rock tunnel based on monitoring data. Background Art

[0002] In actual tunnel construction, the degree of tunnel deformation can be determined by monitoring the arch subsidence and horizontal convergence. At the same time, according to the measured deformation measurement data, timely feedback can be provided and corresponding reinforcement measures can be taken to avoid damage and failure of the support structure. For specific tunnel projects, a comprehensive assessment can be conducted in combination with geological survey reports, construction methods, support structures and other factors to determine the level of tunnel deformation. In the existing soft rock tunnel large deformation level identification operation, the means of analyzing and processing the acquired deformation measurement data are complex and backward, and for complex situations, technical personnel are required to conduct on-site exploration and calculate the data, and then summarize the data for manual identification of the large deformation level of the soft rock tunnel, which is too slow and may also cause inaccurate identification and measurement. Summary of the invention

[0003] In order to solve the problems of low recognition efficiency and inaccurate recognition results in the existing large deformation level identification of soft rock tunnels, the present invention provides a method and device for intelligently identifying the large deformation level of soft rock tunnels based on monitoring data.

[0004] In order to achieve the above-mentioned object of the invention, the present invention provides the following technical solutions:

[0005] In a first aspect, the present invention provides a method for intelligently identifying large deformation levels of soft rock tunnels based on monitoring data, the method comprising:

[0006] Divide the tunnel to be tested into several test sections according to preset intervals;

[0007] A large differential model of the tunnel to be tested is constructed based on the displacement monitoring data of each interval to be tested; the large differential model is used to characterize the displacement change between each interval to be tested;

[0008] A small differential model of the tunnel to be tested is constructed based on the sampling data of each interval to be tested; the small differential model is used to characterize the size data and surrounding rock characteristic data of each interval to be tested;

[0009] Based on the large difference model and the small difference model, a tunnel change model of the tunnel to be tested is simulated and generated by a deep learning algorithm;

[0010] A plurality of tunnel change models in a continuous time are obtained, and the difference values ​​between the tunnel change models are determined according to a time series, and the large deformation level of each interval to be tested in the tunnel to be tested is identified according to the difference values.

[0011] According to a specific implementation, in the above method, the process of generating the tunnel change model includes:

[0012] Fitting is performed according to the displacement change of the large differential model and the size data of the small differential model, and a rectangular fitting frame of each interval to be tested is generated by a deep learning algorithm;

[0013] The rectangular fitting frames are linearly arranged to generate a tunnel change model of the tunnel to be tested.

[0014] According to a specific implementation, the above method further includes:

[0015] Identify the surrounding rock feature data between the tunnel change models, and obtain the adverse geological conditions of each section to be tested in the tunnel to be tested;

[0016] The adverse geological conditions include support deformation, landslide, collapse, surrounding rock sliding deformation, unconstrained deformation of surrounding rock, and local water leakage around the tunnel.

[0017] According to a specific implementation, the above method further includes:

[0018] A large differential model set of the tunnel to be tested is obtained, and a standard deviation is calculated based on the large differential model set to obtain a large deformation change rate of the tunnel to be tested.

[0019] According to a specific implementation, in the above method, the differential value identifies the large deformation level of each section to be tested in the tunnel to be tested, including:

[0020] When the difference value reaches a preset range of the large deformation level, identifying and obtaining the large deformation level corresponding to each interval to be tested;

[0021] The large deformation level includes the first large deformation level, the second large deformation level and the third large deformation level;

[0022] When the difference value exceeds 0.5 mm / t, it is identified as the first level of large deformation;

[0023] When the difference value is between 0.2 mm / t and 0.5 mm / t, it is identified as the second-level large deformation level;

[0024] When the difference value is less than 0.2 mm / t, it is identified as the third level of large deformation;

[0025] Wherein, t is the time series.

[0026] According to a specific implementation, in the above method, the method further includes:

[0027] Take corresponding emergency measures for each large deformation level, including:

[0028] When the large deformation level is level 1, the tunnel support should be strengthened to stabilize the tunnel structure;

[0029] When the large deformation level is level 2, strengthen the initial support and control the construction step distance and excavation cycle advance;

[0030] When the large deformation level reaches Level 3, maintain regular tunnel monitoring.

[0031] In a second aspect, the present invention provides a device for intelligently identifying large deformation levels of soft rock tunnels based on monitoring data, the device comprising:

[0032] A data acquisition module, wherein the data acquisition module comprises a plurality of data acquisition devices, which are arranged in the tunnel to be tested at preset intervals and are used to obtain displacement monitoring data and sampling data of the tunnel to be tested;

[0033] The data processing module is used to divide the tunnel to be tested into a number of sections to be tested according to a preset spacing, and based on the displacement monitoring data and sampling data of the tunnel to be tested obtained by the data acquisition module, adopt any of the above-mentioned methods for intelligently identifying the large deformation level of soft rock tunnels based on monitoring data to obtain the large deformation level of each section to be tested in the tunnel to be tested.

[0034] In a third aspect, the present invention provides an identification device, comprising a memory and a processor; wherein the memory is used to store a computer program; and the processor is used to call and execute the computer program so that the device executes any of the above-mentioned methods for intelligently identifying the large deformation level of a soft rock tunnel based on monitoring data.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] Based on the above scheme, in the process of identifying soft rock deformation in tunnels, the present invention divides the tunnel to be tested into multiple intervals to be tested in a segmented manner, and then constructs a tunnel change model, and relies on the differential value between the models to identify the large deformation level. Compared with the existing manual identification, the efficiency of identification is improved, and the deformation data can be accurately identified within a continuous monitoring period, which effectively improves the risk avoidance ability and solves the problem of complex deformation level determination of soft rock tunnels in the existing deformation identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A schematic diagram of an application scenario provided by an embodiment of the present invention;

[0038] Figure 2 A schematic diagram of a flow chart of a method for identifying large deformation levels of soft rock tunnels provided by an embodiment of the present invention;

[0039] Figure 3 A schematic diagram of a tunnel change model of a tunnel to be tested provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The present invention is further described in detail below in conjunction with test examples and specific implementation methods. However, this should not be understood as the scope of the above subject matter of the present invention being limited to the following embodiments, and all technologies realized based on the content of the present invention belong to the scope of the present invention.

[0041] In the existing soft rock tunnel large deformation level identification operation, the means of analyzing and processing the acquired deformation measurement data are complex and backward. For example, a soft rock tunnel project with a total length of about 10km will be constructed by drilling and blasting method. Displacement monitoring points will be arranged along the tunnel axis, and the monitoring frequency is once a week. Then, Excel, MATLAB and other software will be used to process the displacement monitoring data, and the displacement-time curve will be drawn to analyze the displacement change law. The displacement monitoring data processing and analysis means are relatively complex and backward. The scheme provided by the embodiment of the present invention includes collecting displacement monitoring data during the construction of soft rock tunnels, dividing the soft rock tunnels into multiple data collection areas according to the soft rock tunnel morphology, collecting data on the soft rock tunnel in each data collection area, and then integrating the data of each data collection area to coordinate the soft rock tunnel data. In actual practice, displacement monitoring data during the construction of soft rock tunnels is of great significance for ensuring the safety and stability of tunnel construction. By analyzing the displacement monitoring data, the deformation characteristics of the tunnel surrounding rock can be understood, potential geological disasters can be predicted, and a scientific basis can be provided for adjustment and optimization during the construction process. The present invention takes displacement monitoring data as a research object and analyzes the displacement change law during the construction of soft rock tunnels. Therefore, the embodiment of the present invention generates a soft rock tunnel model and then classifies and divides the model, thereby realizing a technical solution for intelligent identification of soft rock tunnel deformation, and solving the problem of complex soft rock tunnel deformation grade determination in the prior art.

[0042] The technical solution provided by the embodiment of the present invention is further introduced and illustrated below in conjunction with specific implementation methods.

[0043] Please refer to Figure 1 , which shows a schematic diagram of an application scenario provided by an embodiment of the present invention. As shown in the figure, the tunnel to be tested is divided into multiple test intervals according to a preset spacing, and in each test interval, a collection point for monitoring data is arranged according to the actual engineering situation, and data is collected for each test interval.

[0044] The preset spacing is generally determined according to the actual working conditions of the tunnel project. For short and stable soft rock tunnels, the preset spacing can be appropriately widened to save monitoring resources. For long and complex soft rock tunnels, the area where possible deformation can be detected to the greatest extent can be determined within the set test interval based on the survey data during the construction process, so as to determine a reasonable preset spacing.

[0045] Similarly, the collection points are also reasonably arranged according to the working conditions of the tunnel project, so that abnormal data can be detected to the greatest extent. For example, in a soft rock tunnel where a rock fault occurs, the number of collection points can be appropriately increased, while in a hard and continuous interval of the rock mass, the number of collection points can be appropriately reduced, so as to reasonably monitor resources. It should be noted that in order to implement the technical solution of the present invention, no matter how the collection points in each interval to be tested are arranged, the displacement monitoring data, dimension data and surrounding rock characteristic data of each interval to be tested should be collected through the collection points.

[0046] Specifically, please refer to Figure 2 , which shows a schematic flow chart of a method for identifying a large deformation level of a soft rock tunnel provided by an embodiment of the present invention, the method comprising:

[0047] Step 1: Divide the tunnel to be tested into several test sections according to preset intervals;

[0048] Step 2: construct a large difference model of the tunnel to be tested based on the difference in displacement monitoring data between each interval to be tested;

[0049] Step 3: construct a small difference model of the tunnel to be tested based on the sampling data of each section to be tested;

[0050] Step 4: Generate a tunnel change model by simulating the large difference model and the small difference model through a deep learning algorithm;

[0051] Step 5: Acquire a plurality of tunnel change models in a continuous time, determine the difference values ​​between the tunnel change models according to a time series, and identify the maximum deformation level of each interval to be tested in the tunnel to be tested based on the difference values.

[0052] Through the above steps, the present invention constructs a differential value calculation method that can characterize the continuous changes of the tunnel to be tested during the monitoring period of the tunnel to be tested, so as to more accurately identify the large deformation level.

[0053] Specifically, in this implementation, the large differential model is used to characterize the displacement change between each interval to be tested, and the small differential model is used to characterize the size data and surrounding rock characteristic data of each interval to be tested. The method specifically includes: calculating the tunnel displacement change rate based on comprehensive monitoring data, establishing a large differential model s between each interval to be tested, establishing a small differential model p in the data collection area, and coordinating the data discreteness between the large differential model s and the small differential model p. Among them, the data collection of the large differential model s includes the displacement deviation data between two adjacent intervals to be tested and its set S, and the data collection of the small differential model p includes the shape data of the height and width of the soft rock tunnel and the random sampling point data.

[0054] Among them, the calculation formula of the large difference model s is:

[0055]

[0056] Among them, ΔU is the displacement change, ΔT is the time change, and s1 is a large difference model obtained based on the difference between the displacement monitoring data of the second interval to be tested U2 and the first interval to be tested U1;

[0057] Therefore, the set S of large difference models s is

[0058]

[0059] It is understandable that the above parameter T is only a schematic diagram and can be understood as the current moment, that is, the displacement difference or the difference of displacement monitoring data between two adjacent intervals to be tested at the current moment.

[0060] The above data dispersion includes the statistics of the standard deviation of the large differential model set S and the statistics of the tunnel environment model in the small differential model p. Therefore, by calculating the standard deviation based on the large differential model set, the large deformation change rate of the tunnel to be tested can also be obtained, which is reflected in the change level of the soft rock tunnel. The statistics of the tunnel environment model in the small differential model p are simulated and analyzed by stablediffusion software.

[0061] Specifically, in a possible implementation method, based on the small differential model of each test interval obtained at the collection point, the embodiment of the present invention can also identify the surrounding rock characteristic data between the tunnel change models, and obtain the adverse geological conditions of each test interval in the test tunnel; wherein the adverse geological conditions include support deformation, collapse, collapse, surrounding rock sliding deformation, surrounding rock unconstrained deformation, and local water seepage around the tunnel.

[0062] In one possible implementation, an embodiment of the present invention can also use computing power combined with Stable Diffusion software to fit a real-life picture of the inner tunnel change model based on the acquired small differential model, and provide an analysis reference report on the surrounding rock feature data in the real-life picture. The adverse conditions of the soft rock tunnel in each test section can then be summarized through the analysis reference report, thereby further assisting in the repair of the soft rock tunnel.

[0063] Furthermore, the generation process of the tunnel change model includes:

[0064] Fitting is performed according to the displacement change of the large differential model and the size data of the small differential model, and a rectangular fitting frame of each interval to be tested is generated by a deep learning algorithm;

[0065] The rectangular fitting frames are linearly arranged to generate a tunnel change model of the tunnel to be tested.

[0066] Specifically, a rectangular fitting frame is fitted based on the size data of each interval to be tested, the long side represents the height of the interval to be tested, and the narrow side represents the width of the interval to be tested. The rectangular fitting frames fitted to each interval to be tested are linearly arranged to obtain an array rectangular frame, which is restored to a tunnel to be tested composed of several rectangular frames from a bird's-eye view. The center line of the array rectangular frame is regarded as the displacement change center line. When all the array rectangular frames are arranged together, the overall displacement change of the tunnel to be tested is regarded as zero. Based on this, the displacement change rate is determined by the difference between the displacement monitoring data of adjacent intervals to be tested. At this time, the displacement change rate is regarded as the displacement change center line, that is, the difference between the center line connection points of the front and rear rectangular frames of the tunnel to be tested is the difference between the displacement monitoring data of adjacent intervals to be tested. Thus, an array rectangular frame for characterizing the displacement change rate is obtained, that is, the tunnel change model.

[0067] In a possible implementation, the present invention uses Stable Diffusion software to construct the tunnel change model. Figure 3, which shows a schematic diagram of a tunnel change model of a tunnel to be tested provided by an embodiment of the present invention. The tunnel change model simulation by the deep learning algorithm in the stable diffusion software also includes: the stable diffusion software linearly arranges all large differential models (specifically, the stable diffusion change model line in the figure, where each rectangular fitting box is a large differential model, all rectangular fitting boxes are combined into a set S of large differential models, and the lateral distance between the rectangular fitting boxes is the displacement change ΔU), the stable diffusion software performs environmental simulation on the small differential model corresponding to the large differential model, generates a soft rock tunnel environmental model of the large differential model, and the stable diffusion software generates a tunnel change model after integrating all large differential models, which helps to judge and refer to the change rate of the soft rock tunnel.

[0068] It should be noted that Stable Diffusion is an AI painting software based on neural networks. It can automatically create a new painting based on the picture reference provided by the user. Users only need to simply upload the reference picture and set the parameters to easily obtain high-quality and colorful paintings.

[0069] Stable Diffusion has the following characteristics:

[0070] 1. Strong stability and controllability, it can automatically convert text information into high-quality, high-resolution, visually appealing and diverse images.

[0071] 2. Allow users to customize various parameters, such as line thickness, number of colors, etc. All parameters can be modified as needed to obtain better results.

[0072] 3. Use large-scale data sets to ensure that the pictures users want are output quickly and accurately in various situations.

[0073] Therefore, in the embodiment of the present invention, the tunnel change model of the soft rock tunnel can be generated according to the above steps by combining computing power with Stable Diffusion software.

[0074] Specifically, several tunnel change models in continuous time were obtained during the monitoring period. Based on each tunnel change model, the set N j It represents the displacement change rate of each interval to be tested, expressed as:

[0075] N j =[X1, X2, …X n ],

[0076] Among them, N j is the j-th tunnel variation model.n Indicates the displacement change rate of the nth interval to be tested.

[0077] Then determine the difference between the tunnel change models according to the time series, that is, M = [N2-N1, N3-N2, ... N j -N j-1 ].

[0078] The difference value calculation between the adjacent sequence tunnel change models is obtained through the difference in displacement change rate between the corresponding intervals to be tested. This is used to determine the large deformation level of each interval to be tested. The change rate of the soft rock tunnel can be calculated based on the difference value. If the value is smaller, it proves that the change rate of the soft rock tunnel is smaller and more normal; if the value is larger, it proves that the change rate of the soft rock tunnel and the tunnel problem are greater. Specifically, when the difference value reaches the preset range of the large deformation level, the large deformation level corresponding to each interval to be tested is identified;

[0079] For example, in combination with the field investigation and monitoring data of this embodiment, a differential model of the change rate of a soft rock tunnel in a certain section to be tested is proposed.

[0080] The following is a simple example of differential model data, containing data from 5 time points:

[0081]

[0082] Among them, t-2, t-1, t0, t1, and t2 are consecutive sampling time points, 10, 15, 20, 24, and 28 are observation values ​​at consecutive sampling time points, and -, 5, 5, 4, and 4 are differential values ​​calculated by the model.

[0083] Therefore, the change rate of the soft rock tunnel in the test section can be calculated based on the differential value. If the value is smaller, it proves that the change rate of the soft rock tunnel is smaller and more normal. If the value is larger, it proves that the change rate of the soft rock tunnel is larger and the tunnel problem is greater.

[0084] In this example, we have a time series data with observations at 5 time points. The difference value is the difference between the observations at adjacent time points. For the first time point t-2, there is no previous time point, so the difference value is "-".

[0085] Specifically, in the embodiment of the present application, the large deformation level includes a primary large deformation level, a secondary large deformation level, and a tertiary large deformation level;

[0086] When the difference value exceeds 0.5 mm / t, it is identified as the first level of large deformation;

[0087] When the difference value is between 0.2 mm / t and 0.5 mm / t, it is identified as the second-level large deformation level;

[0088] When the difference value is less than 0.2 mm / t, it is identified as the third level of large deformation;

[0089] Among them, t is the time series, corresponding to the above parameter j.

[0090] In the embodiment of the present invention, tunnel response measures are taken according to the tunnel large deformation level, including but not limited to tunnel support reinforcement measures, tunnel drainage measures and tunnel controlled blasting measures. Correspondingly, when the large deformation level is the first large deformation level, the tunnel support is strengthened to stabilize the tunnel structure; when the large deformation level is the second large deformation level, the initial support is strengthened, and the construction step and excavation cycle advance are controlled; when the large deformation level is the third large deformation level, conventional tunnel monitoring is maintained.

[0091] The working principle of the present invention is: by studying the displacement monitoring data during the construction of soft rock tunnels, an analysis method for displacement monitoring data and identification of large deformation levels are provided. Displacement monitoring data plays an important role in the construction of soft rock tunnels, and can provide a basis for construction safety, geological disaster prediction, construction plan optimization, and project quality improvement. In future work, the processing and analysis methods of displacement monitoring data will be further explored to provide more accurate prediction and control for tunnel construction;

[0092] Based on the above technical solution, the present invention divides the tunnel to be tested into multiple test intervals in a segmented manner, and then constructs a tunnel change model, and relies on the differential values ​​between models to identify the large deformation level. Compared with the existing manual identification, the efficiency of identification is improved, and the deformation data can be accurately identified within a continuous monitoring period, which effectively improves the risk avoidance capability and solves the problem of complex deformation level determination of soft rock tunnels in the existing deformation identification.

[0093] Furthermore, an embodiment of the present invention also provides a device for intelligently identifying large deformation levels of soft rock tunnels based on monitoring data, the device comprising:

[0094] A data acquisition module, wherein the data acquisition module comprises a plurality of data acquisition devices, which are arranged in the tunnel to be tested at preset intervals and are used to obtain displacement monitoring data and sampling data of the tunnel to be tested;

[0095] The data processing module is used to divide the tunnel to be tested into a number of sections to be tested according to a preset spacing, and based on the displacement monitoring data and sampling data of the tunnel to be tested obtained by the data acquisition module, adopt any of the above-mentioned methods for intelligently identifying the large deformation level of soft rock tunnels based on monitoring data to obtain the large deformation level of each section to be tested in the tunnel to be tested. For details, please refer to the detailed description in the method example, which will not be repeated here.

[0096] In addition, an embodiment of the present invention also provides an identification device, which includes a memory and a processor; wherein the memory is used to store a computer program; the processor is used to call and execute the computer program, so that the device executes any of the above-mentioned methods for intelligently identifying the large deformation level of a soft rock tunnel based on monitoring data.

[0097] It should be understood that the processor in the embodiment of the present invention can be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method embodiment can be completed by the hardware integrated logic circuit in the processor or the instruction in the form of software. The above processor can be a general processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiment of the present invention can be directly embodied as a hardware decoding processor to perform, or the hardware and software modules in the decoding processor can be combined to perform. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0098] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM (DR RAM). It should be noted that the memory described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0099] It should be understood that the device disclosed in the embodiment of the present invention can be implemented in other ways. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the communication connection between modules can be through some interfaces, servers or indirect coupling or communication connection, which can be electrical or other forms.

[0100] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each module may exist physically separately, or two or more modules may be integrated into one processing unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional unit.

[0101] If the integrated unit is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0102] Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way for easy understanding.

[0103] In addition, in the description of the embodiments of the present invention, it should be noted that, for ordinary technicians in the field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0104] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for intelligently identifying large deformation levels of soft rock tunnels based on monitoring data, characterized in that: The method comprises: Divide the tunnel to be tested into several test sections according to preset intervals; A large differential model of the tunnel to be tested is constructed based on the displacement monitoring data of each interval to be tested; the large differential model is used to characterize the displacement change between each interval to be tested; A small differential model of the tunnel to be tested is constructed based on the sampling data of each interval to be tested; the small differential model is used to characterize the size data and surrounding rock characteristic data of each interval to be tested; Based on the large difference model and the small difference model, a tunnel change model of the tunnel to be tested is simulated and generated through a deep learning algorithm; a plurality of the tunnel change models in a continuous time are obtained, and the difference values ​​between the tunnel change models are determined according to a time series, and the large deformation level of each interval to be tested in the tunnel to be tested is identified according to the difference values.

2. The method for intelligently identifying large deformation levels of soft rock tunnels based on monitoring data according to claim 1 is characterized in that: The generation process of the tunnel change model includes: Fitting is performed according to the displacement change of the large differential model and the size data of the small differential model, and a rectangular fitting frame of each interval to be tested is generated by a deep learning algorithm; The rectangular fitting frames are linearly arranged to generate a tunnel change model of the tunnel to be tested.

3. The method for intelligently identifying large deformation levels of soft rock tunnels based on monitoring data according to claim 1 is characterized in that: The method further comprises: Identify the surrounding rock feature data between the tunnel change models and obtain the adverse geological conditions of each section to be tested in the tunnel to be tested; the adverse geological conditions include support deformation, collapse, collapse, surrounding rock sliding deformation, surrounding rock unconstrained deformation, and local water seepage around the tunnel.

4. The method for intelligently identifying large deformation levels of soft rock tunnels based on monitoring data according to claim 1 is characterized in that: The method further comprises: A large differential model set of the tunnel to be tested is obtained, and a standard deviation is calculated based on the large differential model set to obtain a large deformation change rate of the tunnel to be tested.

5. The method for intelligently identifying large deformation levels of soft rock tunnels based on monitoring data according to claim 1 is characterized in that: Identifying the large deformation level of each section to be tested in the tunnel to be tested based on the differential value includes: When the difference value reaches a preset range of the large deformation level, identifying the large deformation level corresponding to each interval to be tested; The large deformation level includes the first large deformation level, the second large deformation level and the third large deformation level; When the difference value exceeds 0.5 mm / t, it is identified as the first level of large deformation; When the difference value is between 0.2 mm / t and 0.5 mm / t, it is identified as the second-level large deformation level; When the difference value is less than 0.2 mm / t, it is identified as the third level of large deformation; Wherein, t is the time series.

6. The method for intelligently identifying large deformation levels of soft rock tunnels based on monitoring data according to claim 5 is characterized in that: The method further comprises: Take corresponding emergency measures for each large deformation level, including: When the large deformation level is level 1, the tunnel support should be strengthened to stabilize the tunnel structure; When the large deformation level is level 2, strengthen the initial support and control the construction step distance and excavation cycle advance; When the large deformation level reaches Level 3, maintain regular tunnel monitoring.

7. A device for intelligently identifying large deformation levels of soft rock tunnels based on monitoring data, characterized in that: The device comprises: A data acquisition module, wherein the data acquisition module comprises a plurality of data acquisition devices, which are arranged in the tunnel to be tested at preset intervals and are used to obtain displacement monitoring data and sampling data of the tunnel to be tested; A data processing module is used to divide the tunnel to be tested into a number of sections to be tested according to a preset spacing, and based on the displacement monitoring data and sampling data of the tunnel to be tested obtained by the data acquisition module, adopt the method described in any one of claims 1 to 6 to obtain the maximum deformation level of each section to be tested in the tunnel to be tested.

8. An identification device, characterized in that: The device comprises a memory and a processor; wherein the memory is used to store a computer program; and the processor is used to call and execute the computer program, so that the device executes the method according to any one of claims 1 to 6.

Images