Tunnel surrounding rock dynamic classification and early warning method and related equipment thereof

Abstract

The application provides a tunnel surrounding rock dynamic grading and early warning method and related equipment, through integration of two types of core data sources of static basic data and dynamic monitoring data, overall coverage of geological information is realized; with the aid of the space-time correlation binding mechanism of mileage coordinates and time stamps, the information barrier between static data and dynamic data is broken, ensuring accurate correspondence of different dimension data in spatial position and time dimension, providing a unified data basis for subsequent grading calculation; based on the dynamic weight distribution mechanism of the construction stage, the grading calculation can adapt to the geological characteristics in different periods of tunnel construction, the dynamic update of the quality grade of each tunnel segment surrounding rock is realized through the preset grading standard algorithm, the technical difficulty that the traditional fixed weight grading method cannot adapt to the dynamic evolution of surrounding rock in the whole construction process is solved, and the timeliness and accuracy of surrounding rock grading are significantly improved.

Description

Technical Field

[0001] This invention relates to the field of construction safety and information technology for tunnels in water conservancy and hydropower projects, specifically to a method for dynamic classification and early warning of surrounding rock in tunnels and related equipment. Background Technology

[0002] With the accelerating transformation of the energy structure, hydropower, as a clean and renewable energy source, is experiencing a new surge in development and construction, with numerous water conservancy and hydropower projects extending into the high mountain and canyon areas and deep, complex geological regions of western China. As the core carriers of inter-basin water transfer and hydropower development projects, the construction safety and operational stability of water conservancy and hydropower tunnels directly impact the implementation of national water security and energy security strategies. Against this backdrop, tunnel surrounding rock classification, as a core basis for assessing surrounding rock stability and determining support parameters, plays a decisive role in project safety, cost control, and construction efficiency due to its accuracy, timeliness, and dynamic adaptability.

[0003] In water conservancy and hydropower projects, the classification of surrounding rock in tunnels is the core basis for assessing the stability of the surrounding rock and determining support parameters, but its accuracy and timeliness directly affect the safety of the project. As my country's water conservancy and hydropower projects extend to the high mountain and canyon areas and deep and complex geological areas in the west, the traditional static surrounding rock classification model is no longer able to meet the needs of the projects: on the one hand, water conservancy tunnels are mostly located in remote mountainous areas, and surface exploration conditions are limited. Traditional drilling and geophysical exploration methods are difficult to fully reveal deep geological defects (such as hidden karst conduits and high-pressure aquifers), resulting in insufficient accuracy in geological exploration; on the other hand, during the construction of water conservancy tunnels, dynamic changes such as stress release, seepage field reconstruction, and rock mass disturbance are more intense. In particular, the seepage pressure of high-head tunnels may lead to a sharp deterioration of the mechanical parameters of the surrounding rock, and the static classification results are seriously out of sync with the actual working conditions.

[0004] In other words, how to provide a dynamic classification and early warning method for tunnel surrounding rock to achieve dynamic updating of surrounding rock grade and early warning of anomalies, thereby improving the timeliness and accuracy of surrounding rock classification, is a technical problem that urgently needs to be solved in this field. Summary of the Invention

[0005] This invention provides a method for dynamic classification and early warning of surrounding rock in tunnels, and related equipment thereof, to solve at least one of the above-mentioned technical problems.

[0006] In a first aspect, this application provides a method for dynamic classification and early warning of surrounding rock in tunnels, the method comprising: Acquire multi-source geological data of the target tunnel site, including static basic data and dynamic monitoring data; The dynamic monitoring data is preprocessed to obtain dynamic indicator data, and the dynamic indicator data is spatiotemporally linked and bound to the static basic data based on mileage coordinates and timestamps. Based on the dynamic weight allocation mechanism, the static basic data and the dynamic indicator data are weighted according to the current construction stage; The preset surrounding rock classification standard algorithm is invoked to perform dynamic classification calculation of the surrounding rock based on the static basic data, the dynamic index data, and the weight allocation of the two, so as to obtain the surrounding rock quality level of each section of the target tunnel.

[0007] Optionally, the preprocessing includes: outlier removal, data format standardization, and missing value imputation.

[0008] Optionally, the weight allocation mechanism is as follows: If the current construction phase is the initial stage, then the weight of the static basic data is set to 70%, and the weight of the dynamic indicator data is set to 30%. If the current construction phase is in the middle stage, then the weight of the static basic data is set to 50%, and the weight of the dynamic indicator data is set to 50%. If the current construction phase is the later stage, then the weight of the static basic data is set to 30%, and the weight of the dynamic indicator data is set to 70%. Wherein, the initial stage of construction refers to the first to seventh day after the excavation of the target tunnel; the middle stage of construction refers to the eighth to thirty-day after the excavation of the target tunnel; and the later stage of construction refers to the thirty-first day and above after the excavation of the target tunnel.

[0009] Optionally, the static basic data includes: lithological strength information, structural surface parameter data, primary groundwater distribution information, primary geostress parameters, and rock mass integrity information; The dynamic monitoring data includes in-situ stress monitoring data collected in real time by stress sensors deployed in the target tunnel and groundwater seepage monitoring data collected in real time by seepage flow monitoring instruments deployed in the target tunnel.

[0010] Optionally, the preset surrounding rock classification standard algorithm is one of the following: BQ classification method, improved RMR rock mass classification method, and engineering geological classification method for surrounding rock of water conservancy and hydropower projects.

[0011] Optionally, when the preset surrounding rock grading standard algorithm is the BQ grading method, the step of calling the preset surrounding rock grading standard algorithm to perform dynamic grading calculations on the static basic data, dynamic index data, and weight allocation of each tunnel segment to obtain the surrounding rock quality grade of each tunnel segment within the target tunnel includes: The BQ grading method is used to calculate the surrounding rock classification of each tunnel segment based on the static basic data and the dynamic index data. Specific calculations include: calculating the basic index BQ0 based on the lithological strength information and the rock mass integrity information; calculating the structural plane attitude correction coefficient K2 based on the structural plane parameter data; calculating the groundwater state static correction coefficient based on the primary groundwater distribution information; calculating the ground stress state static correction coefficient based on the primary ground stress parameters; calculating the ground stress state dynamic correction coefficient based on the ground stress monitoring data; and calculating the groundwater state dynamic correction coefficient based on the groundwater seepage flow monitoring data. Based on the weight allocation of the current construction stage, the static correction coefficient and dynamic correction coefficient of groundwater state of each tunnel section are weighted and summed to obtain the comprehensive correction coefficient of groundwater state K1. The static correction coefficient and dynamic correction coefficient of geostress state of each tunnel section are weighted and summed to obtain the comprehensive correction coefficient of geostress state K3. Through formula BQ c =BQ0−100(K1+K2+K3) is used to calculate the final rock mass quality index BQ for each segment of the target tunnel. c ; Based on the final rock mass quality indicators of each tunnel section obtained from the above calculations, and in accordance with the preset rock mass quality indicator grade range, the surrounding rock quality grade of each tunnel section of the target tunnel is determined one by one, thus completing the division of the surrounding rock quality grade of each tunnel section.

[0012] Optionally, the method further includes: Acquire surrounding rock displacement and deformation parameters collected by the surrounding rock convergence monitoring instrument deployed in the tunnel according to a preset time period, advanced forecast data collected by the advanced geological monitoring instrument deployed at the tunnel face, and construction record data recorded synchronously during construction. Based on the static basic data, the dynamic index data, the surrounding rock displacement and deformation parameters, the advanced prediction data, and the construction record data, a three-dimensional geological model of the target tunnel is constructed on the terminal equipment, and the surrounding rock quality grade of each section of the target tunnel is marked with different colors. Configure early warning rules, and when the early warning rules are triggered, generate an early warning report and provide an early warning notification through the terminal device. The content of the early warning report includes the risky section, abnormal data, risk level, and preset handling suggestions. The early warning rules include a graded skip-grade judgment rule and a monitoring index judgment rule. The graded skip-grade judgment rule is used to determine the situation where the quality grade of the surrounding rock drops by a step, and the monitoring index judgment rule is used to determine the situation where the three indicators of convergence rate, stress growth rate and seepage flow change rate show abnormal increases.

[0013] Secondly, this application provides a dynamic classification and early warning system for tunnel surrounding rock, comprising: The data acquisition unit is used to acquire multi-source geological data of the target tunnel site, including static basic data and dynamic monitoring data. The data processing unit is used to preprocess the dynamic monitoring data to obtain dynamic indicator data, and to perform spatiotemporal association binding between the dynamic indicator data and the static basic data based on mileage coordinates and timestamps. The weight allocation unit is used to allocate weights to the static basic data and the dynamic indicator data after association and binding based on the current construction stage, according to the dynamic weight allocation mechanism. The dynamic grading unit is used to call the preset surrounding rock grading standard algorithm, and to perform dynamic grading calculation of the surrounding rock based on the static basic data, the dynamic index data and the weight distribution of the two, so as to obtain the surrounding rock quality level of each section of the target tunnel.

[0014] Thirdly, this application also provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program stored in the memory to implement the tunnel surrounding rock dynamic classification and early warning method described in the first aspect.

[0015] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, characterized in that: when the computer program is executed by a processor, it implements the tunnel surrounding rock dynamic classification and early warning method described in the first aspect.

[0016] Technical effects: This invention achieves comprehensive coverage of geological information by integrating two core data sources: static basic data and dynamic monitoring data. By leveraging the spatiotemporal association binding mechanism of mileage coordinates and timestamps, it breaks down the information barriers between static and dynamic data, ensuring accurate correspondence between data of different dimensions in spatial location and time, providing a unified data foundation for subsequent graded calculations. Based on a dynamic weight allocation mechanism for the construction phase, the graded calculations can adapt to the geological characteristics of different stages of tunnel construction. In the early stages of construction, it mainly relies on static basic data; in the middle and later stages, the weight of dynamic data is gradually increased to respond to real-time changes in the surrounding rock. Finally, a preset graded standard algorithm is used to dynamically update the quality grade of the surrounding rock in each tunnel section. This solves the technical problem that traditional fixed-weight graded methods cannot adapt to the dynamic evolution of the surrounding rock throughout the entire construction process, significantly improving the timeliness and accuracy of surrounding rock grading. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating the dynamic classification and early warning method for tunnel surrounding rock provided in this application; Figure 2 The rendering of the three-dimensional geological model provided for this application; Figure 3 A schematic diagram of a structure for the dynamic classification and early warning system for tunnel surrounding rock provided in this application; Figure 4 A schematic diagram of the structure of the electronic device provided in this application; Figure 5 A schematic diagram of a computer-readable storage medium provided in this application. Detailed Implementation

[0019] This application provides a method and system for dynamic classification and early warning of surrounding rock in tunnels, in order to solve at least one of the above-mentioned technical problems.

[0020] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or modules is not necessarily limited to those explicitly listed, but may include other steps or modules not explicitly listed or inherent to such processes, methods, products, or devices. The naming or numbering of steps appearing in this application does not imply that the steps in the method flow must be performed in the chronological / logical order indicated by the naming or numbering. The execution order of named or numbered process steps can be changed according to the desired technical purpose, as long as the same or similar technical effect is achieved.

[0022] The module division described in this application is a logical division. In practical applications, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the coupling or direct coupling or communication connection between modules shown or discussed may be through some interfaces, and the indirect coupling or communication connection between modules may be electrical or other similar forms, none of which are limited in this application. Furthermore, the modules or sub-modules described as separate components may or may not be physically separated, may or may not be physical modules, or may be distributed in multiple circuit modules. Some or all of the modules may be selected to achieve the purpose of the solution in this application according to actual needs.

[0023] Next, please refer to Figure 1-2 , Figure 1 This is a flowchart illustrating a method for dynamic classification and early warning of tunnel surrounding rock in an embodiment of the present invention. As an embodiment of the method for dynamic classification and early warning of tunnel surrounding rock provided by the present invention, the method includes the following steps S110 to S140: Step S110: Obtain multi-source geological data of the target tunnel site. The multi-source geological data includes static basic data and dynamic monitoring data. Step S120: Preprocess the dynamic monitoring data to obtain dynamic indicator data, and bind the dynamic indicator data with the static basic data in a spatiotemporal relationship based on mileage coordinates and timestamps; As an feasible approach, preprocessing includes outlier removal, data format standardization, and missing value imputation to ensure that the data pass rate after processing is ≥95%.

[0024] Specifically, this application effectively filters out distorted data caused by sensor malfunctions, environmental interference, and other factors through outlier removal, avoiding the negative impact of abnormal data on the classification results. Standardized data format processing unifies the formats of different types of dynamic monitoring data (such as stress data and seepage flow data), removing format barriers for subsequent association and collaborative calculation with static baseline data. Missing value imputation based on time series interpolation algorithms compensates for potential data breakpoints during monitoring, ensuring data integrity and continuity. These three preprocessing operations provide high-quality data input for subsequent weight allocation and classification calculations, improving the accuracy and stability of the surrounding rock classification results from the source.

[0025] The spatial dimension uses tunnel mileage (e.g., K0+000 to K10+000) and three-dimensional geographic coordinates (X, Y, Z) within the tunnel as indexes to associate geological data of each tunnel segment; the temporal dimension uses the data collection timestamp to distinguish between initial data (before construction), construction process data (during construction), and real-time data (monitoring system).

[0026] As an achievable approach, static basic data includes: lithological strength information, structural surface parameter data, primary groundwater distribution information, primary geostress parameters, and rock mass integrity information. The dynamic monitoring data includes in-situ stress monitoring data collected in real time by stress sensors deployed inside the target tunnel and groundwater seepage monitoring data collected in real time by seepage flow monitoring instruments deployed inside the target tunnel.

[0027] Among them, the static basic data is obtained by processing image data of the tunnel face or sidewalls, image shooting distance and inertial sensing data acquired from the target tunnel. The resolution of the image data needs to be ≥1080P, and the inertial sensing data includes three-axis acceleration and three-axis angular velocity.

[0028] Specifically, static foundational data encompasses core geological attributes such as lithological strength and structural parameters, providing stable geological background support for surrounding rock classification and ensuring the fundamental and objective nature of the classification results. Dynamic monitoring data focuses on two key dynamic indicators: in-situ stress and groundwater seepage flow. Real-time acquisition via on-site sensors accurately captures changes in surrounding rock stress and groundwater activity during construction, enabling effective real-time perception of the surrounding rock's response. The specific selection of these two data types aligns with the core requirements of tunnel surrounding rock stability evaluation, ensuring both the foundational basis for classification calculations and real-time capture of dynamic changes in the surrounding rock. This provides targeted and highly practical data support for subsequent dynamic classification and early warning, avoiding classification deviations caused by data redundancy or missing key information.

[0029] As one possible approach, prior to acquiring multi-source geological data from the target tunnel site, the method of this application further includes: Deploy a cloud database on the server side and a 3D visualization and early warning platform on the terminal device side. Configure data storage capacity and data transmission protocol for the cloud database. Complete the installation and commissioning of on-site hardware monitoring equipment in the tunnel, including surrounding rock convergence monitors, stress sensors, seepage flow monitors, etc., and the commissioning qualification rate needs to be ≥98%.

[0030] The cloud database stores data in a "spatiotemporal dual dimension": the spatial dimension uses tunnel mileage and three-dimensional geographic coordinates (X,Y,Z) as indexes to associate data of each tunnel section, and the temporal dimension uses data collection timestamps to distinguish initial data before construction, construction process data, and real-time monitoring data. The following data will be stored in the cloud database: static basic data, dynamic monitoring data before / after preprocessing, spatiotemporal correlation binding relationships of multi-source data, dynamically updated surrounding rock quality grades and early warning and handling logs; if advanced forecast data or construction record data are obtained, they can be stored synchronously. The storage capacity of the cloud database needs to be set according to the specific scale of the tunnel project, with a minimum capacity of ≥100GB. It supports 5G / Ethernet transmission protocols and a transmission rate of ≥100Mbps. When storing advanced forecast data and construction record data, it is necessary to store them in an orderly manner according to the "spatiotemporal dual dimensions" through the data layer interface to ensure data storage integrity of ≥99% in order to meet the needs of the tunnel on-site project.

[0031] Step S130: Based on the dynamic weight allocation mechanism, assign weights to the static basic data and dynamic indicator data after association and binding according to the current construction stage; As one possible approach, the weight allocation mechanism involved in step S130 above is as follows: If the current construction phase is the initial stage, then the weight of static foundation data is set to 70%, and the weight of dynamic indicator data is set to 30%. If the current construction phase is in the middle stage, then the weight of static foundation data is set to 50%, and the weight of dynamic indicator data is set to 50%. If the current construction phase is the later stage, then the weight of static foundation data will be set to 30%, and the weight of dynamic indicator data will be set to 70%. The initial stage of construction refers to the first to seventh day after the excavation of the target tunnel; the middle stage of construction refers to the eighth to thirty-day after the excavation of the target tunnel; and the later stage of construction refers to the thirty-first day and above after the excavation of the target tunnel.

[0032] Specifically, this application quantifies the construction phases (initial stage 1-7 days, mid-stage 8-30 days, and late stage 31 days and above) and clarifies the corresponding weight allocation ratios, making the dynamic weighting mechanism highly operable. This weight allocation method aligns with the characteristics of the surrounding rock at different stages of tunnel construction, solving the problem of fixed weights and inability to dynamically adapt to the construction progress in traditional grading methods. This allows the grading results to accurately reflect the true quality state of the surrounding rock at different construction stages. The weight allocation mechanism can also be adaptively adjusted using engineering analogy or machine learning algorithms.

[0033] Step S140: Call the preset surrounding rock classification standard algorithm, and perform dynamic classification calculation of surrounding rock based on static basic data, dynamic index data and weight allocation to obtain the surrounding rock quality level of each section of the target tunnel.

[0034] As an feasible approach, the preset surrounding rock classification standard algorithm is one of the following: BQ classification method, improved RMR rock mass classification method, and engineering geological classification method for surrounding rock of water conservancy and hydropower projects (HC method). In particular, different classification algorithms can be selected according to different tunnel engineering characteristics or needs.

[0035] As one feasible approach, this application uses the BQ grading method as an example. When the preset surrounding rock grading standard algorithm is the BQ grading method, the step S140 above, which involves calling the preset surrounding rock grading standard algorithm to perform dynamic grading calculations on the static basic data, dynamic index data, and weight allocation of each tunnel segment, to obtain the surrounding rock quality grade of each tunnel segment within the target tunnel, specifically includes the following: The BQ grading method was used to calculate the surrounding rock classification of each tunnel section based on static basic data and dynamic index data. Specific calculations included: calculating the basic index BQ0 based on lithological strength and rock mass integrity information; calculating the structural plane attitude correction coefficient K2 based on structural plane parameter data; and calculating the static correction coefficient K for groundwater state based on primary groundwater distribution information. 1s And the static correction factor K for the geostress state calculated based on the primary geostress parameters. 3s ; Calculate the dynamic correction coefficient K for groundwater state based on groundwater seepage flow monitoring data 1d The dynamic correction coefficient K for the geostress state is calculated based on geostress monitoring data. 3d ; Based on the current weight allocation at each construction stage, the static correction coefficient K for the groundwater state in each tunnel section is determined. 1s and groundwater state dynamic correction coefficient K 1d The weighted summation yields the comprehensive correction coefficient K1 for the groundwater state. The weighted calculation formula for K1 is K1 = X1 * K. 1s +X2*K 1dX1 and X2 are the weighted values ​​of static basic data and dynamic index data, respectively, and K is the static correction coefficient for the geostress state of each tunnel segment. 3s Dynamic correction factor K for geostress state 3d Weighted summation yields the comprehensive correction coefficient K3 for the geostress state. The weighted calculation formula for K3 is K3 = X1 * K. 3s +X2*K 3d ; Through formula BQ c =BQ0−100(K1+K2+K3) is used to calculate the final rock mass quality index BQ for each segment of the target tunnel. c ; Based on the final rock mass quality indicators of each tunnel section obtained from the above calculations, and in accordance with the preset rock mass quality indicator grade range, the surrounding rock quality grade of each tunnel section of the target tunnel is determined one by one, thus completing the division of the surrounding rock quality grade of each tunnel section.

[0036] Specifically, this application takes the BQ grading method as an example, and refines the specific calculation logic of dynamic grading. The separate calculation of static correction coefficient and dynamic correction coefficient not only retains the basic supporting role of static geological data, but also highlights the real-time response value of dynamic monitoring data. Based on the weighted summation mechanism of construction stage weight, the static and dynamic correction coefficients are organically integrated, so that the comprehensive correction coefficient can dynamically adapt to the characteristics of different construction stages.

[0037] As a feasible approach, such as Figure 2 As shown, the method provided in this application further includes the following steps (1)-(3): (1) Obtain the surrounding rock displacement and deformation parameters collected by the surrounding rock convergence monitoring instrument deployed in the tunnel according to the preset time period, the advanced forecast data collected by the advanced geological monitoring instrument deployed at the tunnel face, and the construction record data recorded synchronously during the construction process; (2) Based on static basic data, dynamic index data, surrounding rock displacement and deformation parameters, advanced prediction data and construction record data, a three-dimensional geological model of the target tunnel is constructed on the terminal equipment and the surrounding rock quality grade of each section of the target tunnel is marked with different colors. The surrounding rock quality grades include five levels, from I to V. The real-time surrounding rock grades of different sections of the tunnel are marked with different colors, specifically: Level I is green, Level II is blue, Level III is yellow, Level IV is orange, and Level V is red.

[0038] In the 3D dynamic display, on-site staff can click on different sections of the tunnel 3D model, and pop-up windows will display the time series parameters of multi-source geological data for the corresponding section.

[0039] (3) Configure early warning rules. When an early warning rule is triggered, an early warning report is generated and an early warning prompt is sent through the terminal device. The content of the early warning report includes the risk section, abnormal data, risk level, and preset handling suggestions. The early warning rules include grading and skipping-grade judgment rules and monitoring indicator judgment rules. The grading and skipping-grade judgment rules are used to determine situations where the surrounding rock quality grade drops across grades. The monitoring indicator judgment rules are used to determine situations where the convergence rate, stress growth rate, and seepage flow change rate show abnormal increases. The grading and skipping-grade judgment rules can be implemented using rules such as a drop from Grade III to Grade V within 24 hours, or from Grade II to Grade IV within 72 hours. The monitoring indicator judgment rules can be implemented using rules such as a convergence rate > 5 mm / day, a stress growth rate > 20% / day, and a seepage flow change rate > 30% / day. These thresholds can be customized according to engineering geological conditions.

[0040] Specifically, this application integrates multi-dimensional information such as surrounding rock displacement and deformation parameters, advanced forecast data, and construction record data to construct a three-dimensional geological model that can intuitively present the quality grade of the surrounding rock in each tunnel section (marked with different colors) and the time-series parameters of multi-source geological data for each tunnel section. This achieves a visual representation of the grading results, facilitating engineers to quickly grasp the distribution of the surrounding rock status throughout the tunnel. The early warning report contains core information such as risky tunnel sections and disposal suggestions. Combined with early warning prompts from terminal equipment, it can quickly push risk information and guide engineers to take targeted disposal measures, effectively shortening the risk response time, reducing the probability of engineering safety accidents, and realizing closed-loop management of "grading-visualization-early warning-disposal".

[0041] Compared with the prior art, the present invention has the following beneficial effects: (1) Prominent dynamism: Real-time updates of surrounding rock grade are achieved through dynamic weighting mechanism, making the grading results more consistent with the actual mechanical state of rock mass at the tunnel engineering site, which greatly improves the consistency with actual engineering compared with traditional surrounding rock grading methods. (2) Efficient data fusion: Multi-source geological data fusion solves the problem of "information silos", incorporates long-term field monitoring data into the surrounding rock classification system, and expands the classification basis to "dynamic data" on the basis of "static parameters", thereby improving the accuracy of surrounding rock quality classification; (3) Strong early warning timeliness: The automatic early warning response time has been shortened from several hours to less than 10 minutes, and the prediction timeliness has been greatly enhanced, which has bought critical time for on-site risk management. (4) Intuitive and efficient decision-making: The terminal equipment can realize the linkage display of surrounding rock classification results and multi-source geological data, and engineers can quickly locate the cause of risk and improve the efficiency of on-site decision-making; (5) Standardization of implementation methods: The entire process of system deployment, data collection, fusion processing, hierarchical early warning, and handling feedback is clearly defined to ensure the consistency of technical application in different engineering scenarios and reduce the difficulty of promoting the implementation methods in this application.

[0042] The following case study, using a deep-buried hydropower station's water diversion tunnel (total length 12km, burial depth 500-1200m, lithology mainly granite) as an example, details the implementation process of this system: (1) Project Background A water diversion tunnel is 12km long and 500-1200m deep. The rock is mainly granite, with local faults, water-rich zones and other unfavorable geological features. The tunnel is constructed using the drill-and-blast method, with a designed tunneling cycle of 8 hours per section. It is necessary to achieve dynamic updates and real-time early warning of the surrounding rock grade.

[0043] (2) The specific implementation process is as follows: System Deployment and Parameter Configuration: Deploy a cloud database (500GB capacity), using 5G transmission protocol with a transmission rate of 200Mbps, and configure a web-based 3D visualization and early warning layer; debug 30 sets of surrounding rock convergence monitoring instruments (accuracy ±0.01mm), 20 stress sensors (accuracy ±0.1MPa), and 15 seepage flow monitoring instruments (accuracy ±0.1L / min), with a 100% commissioning pass rate; preset parameters (which can be dynamically adjusted according to different tunnel engineering characteristics): initial dynamic weight values ​​(70% static and 30% dynamic in the initial stage of construction), threshold values ​​for early warning rules (convergence rate > 5mm / day, 24-hour level jump ≥ 2 levels), and data sampling frequency (convergence once / hour, stress once / minute, seepage flow once / day). Multi-source geological data acquisition and storage: Basic data for the K3+200-K3+300 section is collected at the tunnel site, including 1080P images of the tunnel face and sidewalls, lithology, strength, integrity, structural plane attitude (dip, dip angle), trace length, width, groundwater information, maximum initial and maximum stresses and directions, with parameter recording errors not exceeding 3%; On-site dynamic monitoring equipment is activated to collect real-time data on the convergence, stress, and seepage flow of the surrounding rock in this tunnel section, ensuring an online equipment rate of ≥98%; TSP advanced prediction data (e.g., a hidden fault exists at K3+280, 30m from the tunnel face) and construction record data (e.g., excavation advance 3m / day, anchor bolt length 3m) are imported and stored in a cloud database, with data integrity ≥99%.

[0044] Multi-source geological data fusion processing: Preprocessing of dynamic monitoring data from multi-source geological data in the database, mainly including removing abnormal data (exceeding the error range of 3σ), standardizing geological data units, filling missing data (linear interpolation), and ensuring that the qualified rate of the processed data meets the requirements of surrounding rock classification calculation (e.g., exceeding 98%); associating and binding static foundation data at a specific mileage / station with stress data and seepage flow 10 days after construction, with association time ≤ 2 minutes; Dynamic grading calculation: The final rock mass quality index is calculated by weighting the BQ grading method according to the weight allocation mechanism, and the corresponding surrounding rock quality grade is further updated. The rationality is analyzed by comparing with the results of manual review. The dynamic surrounding rock grading results are stored in the cloud database and further synchronized to the terminal device for visualization display and early warning monitoring, with a synchronization delay of ≤30 seconds.

[0045] 3D visualization and early warning system: Different colors are used to display the surrounding rock classification results of different tunnel sections (Level I: green, Level II: blue, Level III: yellow, Level IV: orange, Level V: red). Clicking on any tunnel section displays multi-source data time-series curves (such as the convergence value of the surrounding rock and the change of the final rock mass quality index over the past 30 days). If an early warning rule is triggered (such as a drop from Level III to Level V within 24 hours, a drop from Level II to Level IV within 72 hours, a convergence rate > 5 mm / day, a stress growth rate > 20% / day, a seepage flow change rate > 30% / day, etc.), the system generates an early warning report within 10 minutes and pushes it to 5 managers with a 100% success rate. Managers formulate a response plan within 2 hours: increase the monitoring frequency to 15 minutes / time and prepare steel arch support in advance. The system records the early warning response process, forming a closed-loop management log. During further construction and drilling, no collapse occurred due to timely support, verifying the effectiveness of the system and method.

[0046] The following describes an embodiment of the dynamic classification and early warning system for tunnel surrounding rock in this invention.

[0047] Please see Figure 3 , Figure 3 This is a schematic diagram of an embodiment of the dynamic grading and early warning system for tunnel surrounding rock in this invention. The dynamic grading and early warning system 300 for tunnel surrounding rock includes: Data acquisition unit 301 is used to acquire multi-source geological data of the target tunnel site, including static basic data and dynamic monitoring data; Data processing unit 302 is used to preprocess the dynamic monitoring data to obtain dynamic indicator data, and to perform spatiotemporal association binding between the dynamic indicator data and the static basic data based on mileage coordinates and timestamps; The weight allocation unit 303 is used to allocate weights to the static basic data and the dynamic indicator data after association and binding based on the current construction stage according to the dynamic weight allocation mechanism. The dynamic grading unit 304 is used to call the preset surrounding rock grading standard algorithm, and perform dynamic grading calculation of the surrounding rock based on the static basic data, the dynamic index data and the weight allocation, so as to obtain the surrounding rock quality level of each section of the target tunnel.

[0048] As one possible approach, the preprocessing includes: outlier removal, data format standardization, and missing value imputation.

[0049] As one possible approach, the weight allocation mechanism is as follows: If the current construction phase is the initial stage, then the weight of the static basic data is set to 70%, and the weight of the dynamic indicator data is set to 30%. If the current construction phase is in the middle stage, then the weight of the static basic data is set to 50%, and the weight of the dynamic indicator data is set to 50%. If the current construction phase is the later stage, then the weight of the static basic data is set to 30%, and the weight of the dynamic indicator data is set to 70%. Wherein, the initial stage of construction refers to the first to seventh day after the excavation of the target tunnel; the middle stage of construction refers to the eighth to thirty-day after the excavation of the target tunnel; and the later stage of construction refers to the thirty-first day and above after the excavation of the target tunnel.

[0050] As one possible approach, the static basic data includes: lithological strength information, structural surface parameter data, primary groundwater distribution information, primary geostress parameters, and rock mass integrity information; The dynamic monitoring data includes in-situ stress monitoring data collected in real time by stress sensors deployed in the target tunnel and groundwater seepage monitoring data collected in real time by seepage flow monitoring instruments deployed in the target tunnel.

[0051] As one possible approach, the preset surrounding rock classification standard algorithm is one of the following: BQ classification method, improved RMR rock mass classification method, and engineering geological classification method for surrounding rock of water conservancy and hydropower projects (HC method).

[0052] As one possible approach, when using the BQ grading method, the dynamic grading unit 404 is further configured to perform the following steps: The BQ grading method is used to calculate the surrounding rock classification of each tunnel section based on the static basic data and the dynamic index data. The specific calculations include: calculating the basic index BQ0 based on the lithological strength information and the rock mass integrity information; calculating the structural plane attitude correction coefficient K2 based on the structural plane parameter data; and calculating the groundwater state static correction coefficient K based on the primary groundwater distribution information. 1sAnd based on the primary geostress parameters, calculate the static correction coefficient K for the geostress state. 3s ; Calculate the dynamic correction coefficient K for groundwater state based on the groundwater seepage monitoring data. 1d Based on the aforementioned geostress monitoring data, the dynamic correction coefficient K for the geostress state is calculated. 3d ; Based on the current weight allocation at each construction stage, the static correction coefficient K for the groundwater state in each tunnel section is determined. 1s and groundwater state dynamic correction coefficient K 1d The weighted summation yields the comprehensive correction coefficient K1 for the groundwater state, and the static correction coefficient K for the geostress state of each tunnel section. 3s Dynamic correction factor K for geostress state 3d The weighted summation yields the comprehensive correction coefficient K3 for the geostress state. Through formula BQ c =BQ0−100(K1+K2+K3) is used to calculate the final rock mass quality index BQ for each tunnel segment within the target tunnel. c The quality grade of the surrounding rock for each tunnel section is determined based on the preset national standard grade range.

[0053] Through formula BQ c =BQ0−100(K1+K2+K3) is used to calculate the final rock mass quality index BQ for each segment of the target tunnel. c ; Based on the above calculations, the final rock mass quality index BQ for each tunnel section was obtained. c By comparing with the preset rock mass quality index grade range, the surrounding rock quality grade of each tunnel section of the target tunnel is determined one by one, and the classification of the surrounding rock quality grade of each tunnel section is completed.

[0054] In one possible manner, the data acquisition unit is also configured to perform the following: Acquire surrounding rock displacement and deformation parameters collected by the surrounding rock convergence monitoring instrument deployed in the tunnel according to a preset time period, advanced forecast data collected by the advanced geological monitoring instrument deployed at the tunnel face, and construction record data recorded synchronously during construction. The system also includes: The model building unit is used to build a three-dimensional geological model of the target tunnel on the terminal device based on the static basic data, the dynamic index data, the surrounding rock displacement and deformation parameters, the advanced prediction data and the construction record data, and to mark the surrounding rock quality grade of each section of the target tunnel with different colors. The early warning unit is used to configure early warning rules. When the early warning rules are triggered, an early warning report is generated and an early warning is issued through the terminal device. The content of the early warning report includes the risky section, abnormal data, risk level, and preset handling suggestions. The early warning rules include a graded skip-grade judgment rule and a monitoring index judgment rule. The graded skip-grade judgment rule is used to determine the situation where the quality grade of the surrounding rock drops by a step, and the monitoring index judgment rule is used to determine the situation where the three indicators of convergence rate, stress growth rate and seepage flow change rate show abnormal increases.

[0055] This invention employs a data acquisition unit 301 to acquire multi-source geological data of the target tunnel site, including static basic data and dynamic monitoring data. A data processing unit 302 preprocesses the dynamic monitoring data to obtain dynamic index data, which is then spatiotemporally linked and bound to the static basic data based on mileage coordinates and timestamps. A weight allocation unit 303, using a dynamic weight allocation mechanism, assigns weights to the linked static basic data and dynamic index data according to the current construction stage. A dynamic grading unit 304 invokes a preset surrounding rock grading standard algorithm to perform dynamic grading calculations of the surrounding rock based on the static basic data, the dynamic index data, and the weight allocation, thereby obtaining the surrounding rock quality grade of each section of the target tunnel. This invention solves the technical problem that traditional fixed-weight grading methods cannot adapt to the dynamic evolution of surrounding rock throughout the construction process, significantly improving the timeliness and accuracy of surrounding rock grading. This invention also provides an electronic device, please refer to [link / reference]. Figure 4 , Figure 4 This is a schematic diagram of an embodiment of an electronic device according to the present invention, including: The system includes a memory 401, a processor 402, and a computer program 403 stored in the memory and executable on the processor. When the processor executes the computer program 403 stored in the memory, it implements the above-mentioned intelligent optimization method for tunnel boring machine parameters based on a high-quality dataset.

[0056] For ease of explanation, only the parts related to the embodiments of the present invention are shown. For specific technical details not disclosed, please refer to the section on the intelligent optimization method for shield tunneling parameters based on high-quality datasets in the embodiments of the present invention. The memory 401 can be used to store the computer program 403, which includes software programs, modules, and data. The processor 402 executes the computer program 403 stored in the memory 401 to perform various functional applications and data processing of the electronic device.

[0057] This invention also provides a computer-readable storage medium; please refer to [link to relevant documentation]. Figure 5 , Figure 5 This is a schematic diagram of an embodiment of a computer-readable storage medium in the present invention. The computer-readable storage medium may store a computer program, which, when executed, includes some or all of the steps of the intelligent optimization method for shield tunneling parameters based on high-quality datasets described in the above method embodiments.

[0058] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the devices, electronic equipment and computer-readable storage media described above can be referred to the corresponding process of the intelligent optimization method for shield tunneling parameters based on high-quality datasets in the foregoing method embodiments, and will not be repeated here.

[0059] In the embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between systems or units may be electrical, mechanical, or other forms.

[0060] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0061] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0062] If the integrated unit is implemented as a software functional unit 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0063] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for dynamic classification and early warning of surrounding rock in tunnels, characterized in that, The method includes: Acquire multi-source geological data of the target tunnel site, including static basic data and dynamic monitoring data; The dynamic monitoring data is preprocessed to obtain dynamic indicator data, and the dynamic indicator data is spatiotemporally linked and bound to the static basic data based on mileage coordinates and timestamps. Based on the dynamic weight allocation mechanism, the static basic data and the dynamic indicator data are weighted according to the current construction stage; The preset surrounding rock classification standard algorithm is invoked to perform dynamic classification calculation of the surrounding rock based on the static basic data, the dynamic index data, and the weight allocation of the two, so as to obtain the surrounding rock quality level of each section of the target tunnel.

2. The method according to claim 1, characterized in that: The preprocessing includes: outlier removal, data format standardization, and missing value imputation.

3. The method according to claim 2, characterized in that, The weight allocation mechanism is as follows: If the current construction phase is the initial stage, then the weight of the static basic data is set to 70%, and the weight of the dynamic indicator data is set to 30%. If the current construction phase is in the middle stage, then the weight of the static basic data is set to 50%, and the weight of the dynamic indicator data is set to 50%. If the current construction phase is the later stage, then the weight of the static basic data is set to 30%, and the weight of the dynamic indicator data is set to 70%. Wherein, the initial stage of construction refers to the first to seventh day after the excavation of the target tunnel; the middle stage of construction refers to the eighth to thirty-day after the excavation of the target tunnel; and the later stage of construction refers to the thirty-first day and above after the excavation of the target tunnel.

4. The method according to claim 3, characterized in that: The static basic data includes: lithological strength information, structural surface parameter data, primary groundwater distribution information, primary geostress parameters, and rock mass integrity information. The dynamic monitoring data includes in-situ stress monitoring data collected in real time by stress sensors deployed in the target tunnel and groundwater seepage monitoring data collected in real time by seepage flow monitoring instruments deployed in the target tunnel.

5. The method according to claim 4, characterized in that: The preset surrounding rock classification standard algorithm is one of the following: BQ classification method, improved RMR rock mass classification method, and engineering geological classification method for surrounding rock of water conservancy and hydropower projects.

6. The method according to claim 5, characterized in that, When the preset surrounding rock grading standard algorithm is the BQ grading method, the preset surrounding rock grading standard algorithm is invoked to perform dynamic grading calculations on the static basic data, dynamic index data, and weight allocation of each tunnel segment to obtain the surrounding rock quality level of each tunnel segment within the target tunnel, including: The BQ grading method is used to calculate the surrounding rock classification of each tunnel segment based on the static basic data and the dynamic index data. Specific calculations include: calculating the basic index BQ0 based on the lithological strength information and the rock mass integrity information; calculating the structural plane attitude correction coefficient K2 based on the structural plane parameter data; calculating the groundwater state static correction coefficient based on the primary groundwater distribution information; calculating the ground stress state static correction coefficient based on the primary ground stress parameters; calculating the ground stress state dynamic correction coefficient based on the ground stress monitoring data; and calculating the groundwater state dynamic correction coefficient based on the groundwater seepage flow monitoring data. Based on the weight allocation of the current construction stage, the static correction coefficient and dynamic correction coefficient of groundwater state of each tunnel section are weighted and summed to obtain the comprehensive correction coefficient of groundwater state K1. The static correction coefficient and dynamic correction coefficient of geostress state of each tunnel section are weighted and summed to obtain the comprehensive correction coefficient of geostress state K3. Through formula BQ c =BQ0−100(K1+K2+K3) is used to calculate the final rock mass quality index BQ for each segment of the target tunnel. c ; Based on the final rock mass quality indicators of each tunnel section obtained from the above calculations, and in accordance with the preset rock mass quality indicator grade range, the surrounding rock quality grade of each tunnel section of the target tunnel is determined one by one, thus completing the division of the surrounding rock quality grade of each tunnel section.

7. The method according to claim 6, characterized in that, The method further includes: Acquire surrounding rock displacement and deformation parameters collected by the surrounding rock convergence monitoring instrument deployed in the tunnel according to a preset time period, advanced forecast data collected by the advanced geological monitoring instrument deployed at the tunnel face, and construction record data recorded synchronously during construction. Based on the static basic data, the dynamic index data, the surrounding rock displacement and deformation parameters, the advanced prediction data, and the construction record data, a three-dimensional geological model of the target tunnel is constructed on the terminal equipment, and the surrounding rock quality grade of each section of the target tunnel is marked with different colors. Configure early warning rules, and when the early warning rules are triggered, generate an early warning report and provide an early warning notification through the terminal device. The content of the early warning report includes the risky section, abnormal data, risk level, and preset handling suggestions. The early warning rules include a graded skip-grade judgment rule and a monitoring index judgment rule. The graded skip-grade judgment rule is used to determine the situation where the quality grade of the surrounding rock drops by a step, and the monitoring index judgment rule is used to determine the situation where the three indicators of convergence rate, stress growth rate and seepage flow change rate show abnormal increases.

8. A dynamic classification and early warning system for tunnel surrounding rock, characterized in that, The system includes: The data acquisition unit is used to acquire multi-source geological data of the target tunnel site, including static basic data and dynamic monitoring data. The data processing unit is used to preprocess the dynamic monitoring data to obtain dynamic indicator data, and to perform spatiotemporal association binding between the dynamic indicator data and the static basic data based on mileage coordinates and timestamps. The weight allocation unit is used to allocate weights to the static basic data and the dynamic indicator data after association and binding based on the current construction stage, according to the dynamic weight allocation mechanism. The dynamic grading unit is used to call the preset surrounding rock grading standard algorithm, and to perform dynamic grading calculation of the surrounding rock based on the static basic data, the dynamic index data and the weight distribution of the two, so as to obtain the surrounding rock quality level of each section of the target tunnel.

9. An electronic device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program stored in the memory, implements the tunnel surrounding rock dynamic classification and early warning method as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the tunnel surrounding rock dynamic classification and early warning method as described in any one of claims 1 to 7.

Images