Intelligent early warning cloud platform for complex geological deep tunnel / roadway rockburst disasters

Abstract

The invention discloses an intelligent early warning cloud platform for complex geological deep tunnel / roadway rockburst disasters, and belongs to the technical field of tunnel / roadway rockburst disaster intelligent monitoring. The intelligent early warning cloud platform comprises a multi-source intelligent sensing module and a data intelligent analysis and early warning module. According to the invention, through the exploration construction unit and the detection modeling unit, the front geology is continuously predicted and modeled before and during construction, a risk area is calibrated in advance, and early discovery of risks is realized; a three-dimensional geology and tunnel model is established and continuously corrected, and detection, excavation and monitoring results are marked in the model in real time, so that the risk position, probability and development trend are clear at a glance; analyzing rockburst precursor information through a micro-seismic monitoring unit, and establishing different grades of rockburst early warning criteria based on micro-seismic parameters; the rock mass damage criterion based on the energy dissipation principle is established through the trend monitoring deduction unit, and understanding of the rock burst evolution law is deepened from the mechanics essence.

Description

Technical Field

[0001] This invention relates to the field of intelligent monitoring technology for rockburst disasters in tunnels / roadways, specifically to an intelligent early warning cloud platform for rockburst disasters in deep-buried tunnels / roadways with complex geology. Background Technology

[0002] Rockbursts, a typical deep-seated high-stress geological hazard, pose an increasingly serious constraint on safe and efficient on-site construction as the depth of mineral resource mining and the construction of deep underground tunnels and mine roadways continue to increase. If the risk of rockbursts can be accurately detected in advance through multi-source information and warning signals can be sent to the construction site, the threat of rockbursts to on-site workers and equipment can be reduced or avoided. Therefore, advanced geological forecasting is of great significance for safe tunnel construction. However, current advanced geophysical forecasting methods for tunnels still have the following problems:

[0003] (1) At present, there is no relatively mature and complete system in the field of geological advance prediction. The coordination between various geological prediction methods is not enough. The application level of modern information technology in tunnel / roadway advance geological prediction is relatively low. There is no complete set of computer-aided software for tunnel / roadway advance geological prediction for prediction professionals.

[0004] (2) The content of advanced geological forecasting is mainly limited to the forecasting of basic geological conditions and adverse geological bodies of tunnels. There is very little research on the forecasting of engineering geological disasters induced by construction with complex formation mechanisms such as rock bursts, large deformations, karst, and sudden water inrush. The forecasting and risk management of the above-mentioned engineering geological disasters are not timely.

[0005] (3) In the process of tunnel / roadway advance prediction, advance geological prediction work should be incorporated into the construction process management. The whole process requires the cooperation and coordination of various departments such as owner, geology, design, construction, supervision and exploration, and timely exchange of data and feedback information. However, in the current prediction process, the division of labor among departments is chaotic, the cooperation is disordered, data processing and information management are slow and untimely, and the efficiency is low. There is a lack of a mature system and a system platform for information exchange and data transmission among departments.

[0006] Based on this, the present invention designs a smart early warning cloud platform for rockburst disasters in complex geological deep-buried tunnels / tunnels, in order to solve the above problems. Summary of the Invention

[0007] The purpose of this invention is to provide a smart early warning cloud platform for rockburst disasters in deep-buried tunnels / roadways with complex geology, so as to solve the problems mentioned in the background art.

[0008] To achieve the above objectives, the present invention provides the following technical solution:

[0009] A smart early warning cloud platform for rockburst disasters in complex geological deep-buried tunnels / tunnels, including data acquisition equipment and servers;

[0010] The data acquisition device communicates with the server via the Internet of Things (IoT), and is connected via the IoT to several sensors installed in the tunnel, which are designated as sensor 1, sensor 2, ..., sensor n.

[0011] The server is equipped with a multi-source intelligent sensing module and a data intelligent analysis and early warning module.

[0012] The multi-source intelligent sensing module is used to conduct advanced geological exploration of tunnels, establish three-dimensional tunnel models, and derive the rockburst susceptibility patterns under different geological conditions. It is also used to sense stress field changes, establish stress-strain thresholds for different rockburst levels, obtain stress concentration states and rockburst risk probabilities under different types of geological information, and monitor the damage status of tunnel rock mass.

[0013] The data intelligent analysis and early warning module is used for advanced detection and precise modeling of complex geological structures, monitoring and prediction of the development trend of micro-fractures, and intelligent early warning.

[0014] Preferably, the multi-source intelligent sensing module includes:

[0015] The exploration and construction unit conducts advanced geological exploration of the tunnel to be excavated, records the location of adverse geological conditions characterized by large wave velocity variations, and initially marks them as rockburst risk zones; then, a tunnel model is established, and the exploration results are marked in the tunnel model;

[0016] The information collection unit collects daily tunnel excavation data, marks or records it in the three-dimensional tunnel model, and compares the rockburst occurrence results under different geological conditions to obtain the rockburst susceptibility patterns under different geological conditions.

[0017] The monitoring and sensing unit senses changes in the stress field, establishes stress-strain thresholds for different rockburst levels, and obtains stress concentration states and rockburst risk probabilities under different types of geological information.

[0018] The microseismic monitoring unit uses microseismic monitoring methods to monitor the damage status of the tunnel rock mass in real time.

[0019] Preferably, the monitoring and sensing unit includes stress and strain sensors arranged around the tunnel to observe the stress and strain patterns before and after rockbursts and at different construction stages, and the correspondence between rockbursts of different grades, to establish stress and strain thresholds for different rockburst grades, to refine the risk zone or time period of rockbursts, and to obtain stress concentration states and rockburst risk probabilities under different types of geological information in combination with geological information.

[0020] Preferably, the microseismic monitoring unit uses microseismic monitoring methods to monitor the damage state of the tunnel rock mass in real time, and includes the following steps:

[0021] A mobile microseismic monitoring method was used to monitor the damage state of the tunnel rock mass in real time, obtain microseismic information before and after rockburst, establish the correspondence between microseismic parameters and rockburst, analyze the precursor information and evolution law of rockbursts of different levels, and establish early warning criteria for rockbursts of corresponding levels.

[0022] Based on the established early warning criteria, before a medium- or higher-level rock eruption occurs, a text message or WeChat message is sent to the corresponding smart terminal to provide real-time dynamic intelligent early warning reminders.

[0023] Preferably, the data intelligent analysis and early warning module includes:

[0024] The detection and modeling unit is used for advanced detection and precise modeling of complex geological structures;

[0025] The trend monitoring and simulation unit is used to monitor and simulate the development trend of microfractures.

[0026] The intelligent early warning unit, based on the results of various advanced geological explorations, precise simulation of geological structure stress fields, and microseismic monitoring and simulation, divides tunnel geological hazard forecasts into long-term early warning, short-term early warning, and real-time early warning.

[0027] Preferably, the working process of the detection modeling unit includes the following steps:

[0028] Information was collected regarding the geological and construction conditions at the site;

[0029] The collected geological information is classified and summarized to infer the possible geological conditions in front of the excavation face and to establish a three-dimensional geological model. At the same time, geological information behind the excavation face is collected and processed in a timely manner. The accuracy of the established three-dimensional geological model is verified based on geological information such as the degree of fragmentation and water content of the exposed surrounding rock mass, and the established three-dimensional geological model is continuously corrected.

[0030] The three-dimensional geological model was read using graphic scanning software, a three-dimensional finite element numerical model was constructed, and the three-dimensional mesh was densified by interpolation using the octree algorithm, thereby calibrating the physical and mechanical parameters of the overall model and deducing the stress field of the original rock.

[0031] Preferably, the working process of the trend monitoring and inference unit includes the following steps:

[0032] 24-hour real-time monitoring of rock microfractures induced by on-site construction disturbances; collection of microseismic information of rock mass in different construction sections; analysis of the spatiotemporal intensity distribution or evolution characteristics of the collected microseismic events; assessment of the current damage state of rock mass under the influence of excavation disturbances; and inference and prediction of the orientation of unknown geological defect structures and their catastrophic evolution characteristics based on the microseismic distribution characteristics.

[0033] Based on the principle of energy dissipation, and combined with the source information obtained from microseismic monitoring, we analyze the relationship between rock mass type, strength and fracture distribution characteristics and microseismic event rate and energy rate in different stages of microseismic activity evolution.

[0034] The relationship between energy loss from microseismic damage and changes in the physical and mechanical parameters of rock mass was analyzed. A rock mass damage criterion considering microseismic energy dissipation was established. At the same time, large-scale scientific calculation feedback analysis was conducted to analyze the microseismic damage effect during the progressive failure process of rock mass.

[0035] Compared with the prior art, the beneficial effects of the present invention are:

[0036] 1. This invention uses exploration construction units and detection modeling units to continuously predict and model the geology ahead before and during construction, identify risk areas in advance, and achieve early detection of risks;

[0037] 2. This invention establishes and continuously refines a three-dimensional geological and tunnel model, marking the detection, excavation, and monitoring results in the model in real time, making the risk location, probability, and development trend clear at a glance;

[0038] 3. This invention analyzes rockburst precursor information through a microseismic monitoring unit, establishes rockburst early warning criteria for different levels based on microseismic parameters, and establishes a rock mass damage criterion based on the principle of energy dissipation through a trend monitoring and deduction unit, thus deepening the understanding of the evolution law of rockburst from a mechanical perspective. Attached Figure Description

[0039] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of 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.

[0040] Figure 1 This is a block diagram illustrating the overall principle of the present invention;

[0041] Figure 2 This is a schematic diagram of the internal structure of the server in this invention;

[0042] Figure 3 This is a schematic diagram of the multi-source intelligent sensing module of the present invention;

[0043] Figure 4 This is a schematic diagram of the data intelligent analysis and early warning module of the present invention;

[0044] Figure 5 This is a schematic diagram of the installation of the sensor of the present invention.

[0045] The attached diagram lists the components represented by each number as follows:

[0046] 100 - Data acquisition equipment;

[0047] 200-Server;

[0048] 210-Multi-source intelligent sensing module, 211-Exploration and construction unit, 212-Information acquisition unit, 213-Monitoring and sensing unit, 214-Microseismic monitoring unit;

[0049] 220 - Data intelligent analysis and early warning module; 221 - Detection and modeling unit; 222 - Trend monitoring and inference unit; 223 - Intelligent early warning unit. Detailed Implementation

[0050] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0051] Example 1

[0052] Please refer to the accompanying drawings. This invention provides a technical solution:

[0053] A smart early warning cloud platform for rockburst hazards in deep tunnels / roadways with complex geology, such as Figure 1 As shown, it includes a data acquisition device 100 and a server 200;

[0054] The data acquisition device 100 communicates with the server 200 via the Internet of Things (IoT), and is also connected via the IoT to several sensors installed inside the tunnel, designated as sensor 1, sensor 2, ..., sensor n. Some of the sensors are installed in the tunnel as follows: Figure 5 As shown; several sensors are various high-precision and high-stability sensors to meet the needs of possible extreme or complex environments, and are used to acquire data on multiple key parameters in the tunnel, such as pressure, strain, temperature and humidity.

[0055] like Figure 2 As shown, the server 200 is equipped with a multi-source intelligent sensing module 210 and a data intelligent analysis and early warning module 220.

[0056] The multi-source intelligent sensing module 210 is used to conduct advanced geological exploration of tunnels, establish three-dimensional tunnel models, and derive the rockburst susceptibility patterns under different geological conditions; it is also used to sense stress field changes, establish stress-strain thresholds for different rockburst levels, obtain stress concentration states and rockburst risk probabilities under different types of geological information, and monitor the damage state of tunnel rock mass.

[0057] The data intelligent analysis and early warning module 220 is used for advanced detection and precise modeling of complex geological structures, monitoring and prediction of the development trend of micro-fractures, and intelligent early warning.

[0058] I. Multi-source intelligent sensing module

[0059] like Figure 3 As shown, the multi-source intelligent sensing module 210 includes an exploration and construction unit 211, an information acquisition unit 212, a monitoring and sensing unit 213, and a microseismic monitoring unit 214.

[0060] (1) Exploration and construction unit

[0061] The exploration construction unit 211 conducts advanced geological exploration of the tunnel to be excavated using methods such as TSP geophysical exploration or ground-penetrating radar, records the location of adverse geological conditions characterized by large wave velocity variations, and initially marks them as rockburst risk zones; then, a three-dimensional tunnel model is established, and the exploration results are marked in the three-dimensional tunnel model.

[0062] The specific process of exploration using the TSP geophysical method is as follows:

[0063] Survey lines are arranged on one or both sides of the tunnel. Several collection points and receivers are set on the survey lines. The distance between the collection points and receivers is in the range of 10 to 20 meters, specifically 15 meters. The first collection point on the survey line is 20 meters away from the tunnel face.

[0064] A small number of seismic sources are set up within the acquisition point to excite seismic waves. Raw recorded data is obtained through a receiver. The signal-to-noise ratio of the raw recorded data is checked for consistency, and invalid channels caused by poor coupling or duds are removed. High-frequency noise and low-frequency drift are filtered out using a bandpass filter. The arrival times of direct P-waves and S-waves are automatically picked up using the energy ratio method or AIC algorithm, and the P-wave and S-wave components are separated. An initial velocity model is established and optimized through iterative inversion. Specifically, velocity scanning is performed using the common reflection point (CRP) superposition method, and the superposition energy is maximized through iteration to obtain the P-wave velocity V. p transverse wave velocity V s Wave speed ratio V p / V s profile;

[0065] The Kirchhoff depth migration method is used to locate reflection events to their true spatial locations. An amplitude threshold is set, and strong reflection phase axes are tracked. Strong reflection surfaces are identified and extracted from the migration data volume, thereby obtaining the wave velocity distribution and reflection interface of the rock mass in front of the tunnel face, which is the TSP data.

[0066] The specific process of exploration using ground-penetrating radar is as follows: a grid of survey lines is laid out at the tunnel face, and continuous longitudinal survey lines are laid out at the tunnel arch, sidewalls, and arch bottom. Radar data within a range of 20-50 meters ahead is detected through the survey lines. The radar data is processed to construct a two-dimensional grayscale map or color map radar image profile. The boundary of the abnormal area is delineated on the radar image profile, which is the anomaly.

[0067] The TSP data and the anomaly data from the ground-penetrating radar are used as the detection results. The detection results are then converted into a common format and imported into the three-dimensional tunnel model.

[0068] The specific process of exploration using ground-penetrating radar is as follows:

[0069] A grid of survey lines is laid out at the tunnel face, and continuous longitudinal survey lines are laid out on the tunnel arch, sidewalls, and arch bottom. Radar data within a range of 20-50 meters ahead is detected through the survey lines. The radar data is processed to construct a two-dimensional grayscale map or color map radar image profile. The boundary of the abnormal area is delineated on the radar image profile, which is the anomaly.

[0070] The TSP data and the anomaly data from the ground-penetrating radar are the detection results. The detection results are then converted into a common format and imported into the three-dimensional tunnel model.

[0071] (2) Information collection unit

[0072] Information collection unit 212 collects daily tunnel excavation data, marks or records it in the three-dimensional tunnel model, and compares the rockburst occurrence results under different geological conditions to obtain the rockburst susceptibility patterns under different geological conditions, thereby providing a scientific basis for high-intensity rockburst early warning and control.

[0073] The specific process of comparing the results of rock burst generation under different geological conditions is as follows:

[0074] Mark the locations where rockbursts have occurred on the wave velocity ratio profile, count the wave velocity ratio intervals in the rockburst occurrence area, and mark or record the areas in the three-dimensional tunnel model whose wave velocity ratios fall within the wave velocity ratio intervals of the rockburst occurrence area.

[0075] The spatial relationship between rockburst events and TSP strong reflective interfaces is statistically analyzed. The frequency of rockbursts occurring within 5 meters and 10 meters before and after the strong reflective interface is calculated. The rockburst occurrence results are determined and marked or recorded by comparing the frequency with the corresponding frequency threshold.

[0076] It should be noted that the daily tunnel excavation information includes the daily tunneling mileage, the occurrence of rock bursts on the day, and information on any abnormal geological features or tunnel face sketches.

[0077] (3) Monitoring and sensing unit

[0078] The monitoring and sensing unit 213 senses changes in the stress field, establishes stress-strain thresholds for different rockburst levels, and acquires stress concentration states and rockburst risk probabilities under different types of geological information. Specifically, this includes:

[0079] First, stress and strain sensors are deployed around the tunnel to collect raw stress time series data, which is used to observe the correlation between stress and strain patterns before and after rockbursts and different construction stages and different levels of rockbursts. The absolute value of stress, stress change rate, stress gradient and energy index are extracted from the raw stress time series data.

[0080] Among them, the stress change rate is the rate of increase of stress per unit time, which is an important precursor to rockburst.

[0081] The stress gradient is the rate of change of stress along the borehole depth direction, used to reflect the degree of stress concentration;

[0082] The energy index is the area enclosed by the stress-strain curve and is used to characterize the accumulated elastic strain energy.

[0083] Secondly, stress-strain thresholds for different rockburst levels are established. The absolute value of stress, rate of change of stress, stress gradient, and energy index are compared with the stress-strain thresholds corresponding to different rockburst levels to determine different rockburst levels. This lays the foundation for improving the accuracy and precision of early warning by combining microseismic monitoring results. At the same time, it can further refine the risk zone or time period of rockburst occurrence.

[0084] Finally, by combining geological information, we can obtain the stress concentration state and rockburst risk probability under different types of geological information, laying the foundation for early warning of high-intensity rockbursts. Specifically:

[0085] Geological parameters UCS, D, V were collected. p / V s ... calculate the stress concentration factor K, K = f(UCS, D, V) p / V s ,...)=β0+β1×UCS+β2×D+β3×(V p / V s ) + ... + ε, where UCS is the numerical value of rock strength, D is the numerical value of distance from adverse geological bodies, and V p / V sβ0 is the wave velocity ratio, β1, β2, β3, ... are regression coefficients, representing the weight or influence of geological parameters, and ε is the error term.

[0086] The probability of rockburst risk is obtained as follows:

[0087] Obtain the numerical value of rock strength and wave velocity ratio, set several wave velocity ratio ranges and rock strength ranges to form conditional combinations of wave velocity ratio ranges and rock strength ranges. Each conditional combination corresponds to a probability 1, and each probability 1 corresponds to a specific probability value. Match the obtained numerical value of rock strength and wave velocity ratio with the corresponding several wave velocity ratio ranges and rock strength ranges, and output the corresponding prior probability P1.

[0088] The absolute value of stress and the rate of change of stress are compared with the corresponding thresholds to calculate the likelihood P2, specifically:

[0089] Rock uniaxial compressive strength with an absolute stress value > 0.7 is labeled as event E1; stress change rate with a stress change rate threshold is labeled as event E2. All rockburst data are statistically analyzed, and the number of times events E1 and E2 occur simultaneously before a rockburst occurs is calculated. This number is divided by the total number of rockbursts to obtain the likelihood P2. The prior probability and likelihood are substituted into Bayes' theorem to output the rockburst risk probability P(RB|E).

[0090] Bayes' theorem is as follows:

[0091]

[0092] Wherein, P3 is the false alarm probability of events E1 and E2 occurring simultaneously, which is obtained by dividing the number of false alarms of events E1 and E2 occurring simultaneously by the total number of rockbursts.

[0093] (4) Microseismic monitoring unit

[0094] The microseismic monitoring unit 214 is used to monitor the damage status of tunnel rock mass using microseismic monitoring methods, including the following steps:

[0095] First, a mobile microseismic monitoring method is used to monitor the damage state of the tunnel rock mass in real time, obtain microseismic information before and after the rock burst, and save the data;

[0096] Then, based on the rockburst information, the correspondence between microseismic parameters and rockbursts is established, the precursor information and evolution law of rockbursts of different levels are analyzed, and the early warning criteria for rockbursts of different levels are established.

[0097] Finally, based on the established early warning criteria, before a high-level rockburst (medium and above level rockburst) occurs, a text message or WeChat message is sent to the corresponding smart terminal to provide real-time dynamic intelligent early warning reminders.

[0098] The specific process is as follows: the sensor is installed on a movable bracket and moves forward periodically to monitor as the tunnel face advances; at the same time, sensors are arranged on the tunnel sidewalls, arch, and arch bottom to collect microseismic information of the tunnel, including the arrival time, amplitude, or duration of P-waves and S-waves.

[0099] Based on the arrival time difference and wave velocity model of P-wave and S-wave, the Geiger method or double difference location method is used to calculate the three-dimensional spatial coordinates (x, y, z) of the rupture occurrence, where x is the longitudinal coordinate of the tunnel, and y and z are the cross-sectional coordinates. The three-dimensional spatial coordinates (x, y, z) of all microseismic events within a certain time window are obtained, and the neighborhood distance radius and minimum number of events are set.

[0100] Traverse all event points. If a point has at least a minimum number of points corresponding to the minimum number of events within its neighborhood radius, it constitutes a core point and forms a cluster. All core points reachable within the neighborhood radius are assigned to the same cluster. Event points that do not belong to any cluster are marked as noise points, i.e., discrete events.

[0101] The number of all events assigned to a cluster is counted, and the result is divided by the total number of events to obtain the clustering event ratio, which is then labeled as the event clustering degree R_cluster. The b-value is calculated, where the b-value represents the parameter of the ratio of the number of large and small earthquakes or microseismic events in a region, which is used to reflect the stress level and the uniformity of fracture within the rock mass.

[0102] The specific calculation process is as follows: Select microseismic events within a past time window, detect the magnitude of the microseismic events, and obtain a magnitude set {M1, M2, M3, ..., Mn}, where n is the total number of events; then, use the formula... The value of b is calculated, where e is the natural constant, approximately equal to 2.71828, representing the average magnitude in the magnitude set, and represents the smallest magnitude in the magnitude set;

[0103] Early warning criteria for different levels of rockbursts are established based on the event clustering degree R_cluster and the b value. Clustering degree thresholds R_c1, R_c2, and R_c3 are set for the event clustering degree, and R_c1 < R_c2 < R_c3. If R_cluster ≤ R_c1, and the number of events per day < 10, and the b value > 0.8, it is judged as a low-risk warning. If R_c1 < R_cluster ≤ R_c2, and the number of events per day ∈ (10, 50), and the b value ∈ (0.5, 0.8), it is judged as a medium-risk warning. If R_c2 < R_cluster ≤ R_c3, and the number of events per day ≥ 50, and the b value < 0.7, it is judged as a high-risk warning. If R_c3 < R_cluster, and the b value < 0.5, it is judged as an extremely high-risk warning.

[0104] It should be noted that the time window can be the past 24 hours, 48 ​​hours, or other durations; the neighborhood distance radius is set according to the sensor positioning error and tunnel scale, for example, 5 meters to 20 meters; the minimum number of events is the minimum number of points required for a dense area, such as 5 events.

[0105] II. Data Intelligent Analysis and Early Warning Module

[0106] like Figure 4 As shown, the data intelligent analysis and early warning module 220 includes a detection modeling unit 221, a trend monitoring and deduction unit 222, and an intelligent early warning unit 223.

[0107] (1) Detection Modeling Unit

[0108] The detection and modeling unit 221 is used for advanced detection and precise modeling of complex geological structures, including the following steps:

[0109] First, information on the geology and construction conditions at the site is collected to obtain geological information, including advanced geological exploration before tunnel excavation and geological conditions observed during excavation, so as to control the specific situation of tunnel construction and provide a basis for accurate modeling.

[0110] It should be noted that the on-site construction employed a combination of methods, including geological sketching, TSP seismic wave detection, advanced horizontal drilling, and deepening of blast holes, for advanced geological exploration.

[0111] Information collected through geological sketching includes rock type, weathering degree, joints, fissures, location of faults, attitude (dip angle, strike), spacing, trace length, filling material, and water outflow status (dry, wet, seeping, gushing).

[0112] Information acquired through TSP seismic wave detection includes P-wave velocity V. p transverse wave velocity V s Wave speed ratio V p / V s Profiles of physical and mechanical parameters such as density and Poisson's ratio, as well as the location and attitude of strong reflective interfaces (faults, fracture zones, lithological boundaries);

[0113] Information collected through advanced horizontal drilling includes drilling rate changes, core recovery rate, core morphology, water output, and water pressure.

[0114] Information obtained by deepening the boreholes includes rock powder discharged from the borehole and water discharge.

[0115] Secondly, the collected geological information is categorized and summarized. Through stratigraphic characteristics, elements and tunnel geometric parameters, surface correlation analysis, and geological theory analysis, possible geological conditions ahead of the excavation face are inferred, and a three-dimensional geological model is established. At the same time, the detection results are collected and processed in a timely manner, and the accuracy of the established three-dimensional geological model is verified based on geological information such as the degree of fragmentation and water abundance of the exposed surrounding rock mass. The established three-dimensional geological model is continuously revised, and the revision results can provide a basis for further adjustments to construction plans and methods.

[0116] The specific process is as follows:

[0117] All geological elements in the geological information are classified and standardized in naming, and each geological object is assigned a quantitative attribute and stored in the corresponding database.

[0118] The geological features, elements and tunnel geometric parameters were analyzed. In the 3D modeling software, the tunnel axis was intersected with the geological interface model. The lithological sequence and contact relationship presented on the tunnel face when the tunnel passes through an inclined rock layer at a certain elevation and direction were analyzed.

[0119] Surface correlation analysis is conducted. Using a GIS platform, surface geological mapping, digital elevation model and tunnel axis are overlaid and analyzed. If there is a clear fault line or lithological boundary on the surface, the possible exposure mileage of the fault line at the location of the underground tunnel is inferred based on the stratigraphic attitude.

[0120] Geological analysis is conducted, and rose diagrams or isodensity diagrams are used to analyze the joints exposed at the working face to identify dominant joint sets. Based on their occurrence, the key blocks that may appear ahead, i.e., the rock masses that may become unstable, are inferred.

[0121] All geological data points are used as constraints, including contact points, fault points, and attitude data; smooth, seamless rock strata interfaces and fault surfaces are generated through a three-dimensional geological model.

[0122] Finally, the RFPA-CT graphic scanning software was used to read the three-dimensional geological model, construct a three-dimensional finite element numerical model, and use the octree algorithm to interpolate and refine the three-dimensional mesh, thereby calibrating the physical and mechanical parameters of the overall model and deducing the stress field of the original rock.

[0123] (2) Trend monitoring and inference unit

[0124] Trend monitoring and simulation unit 222 is used to monitor and simulate the development trend of microfractures, including the following steps:

[0125] A microseismic monitoring system is used to monitor the microfractures in the rock mass induced by on-site construction disturbances in real time for 24 hours. Microseismic information of the rock mass in different construction sections is collected, and the spatiotemporal intensity distribution or evolution characteristics of the collected microseismic events are analyzed. The damage state of the current rock mass under the influence of excavation disturbance is assessed, and the orientation of unknown geological defect structures and their catastrophic evolution characteristics are inferred and predicted based on the microseismic distribution characteristics.

[0126] Among them, the microseismic information is processed to generate microseismic records. Each microseismic record includes {number, time, three-dimensional spatial coordinates, magnitude, released energy, stress drop}.

[0127] Calculate the event clustering degree R_cluster, event rate E_R, b-value, and energy release rate ERR, where the event rate is the number of events per unit time; and the energy release rate is the cumulative microseismic energy released per unit time.

[0128] A damage index DI is constructed to determine the damage status, where DI = norm[γ1×R_cluster+γ2×E_R+γ3×(1-b)+γ4×ERR], γ1, γ2, γ3, and γ4 are weight coefficients, and norm[] is the normalization function.

[0129] In the 3D tunnel model, the DI value is calculated based on the microseismic activity within each grid cell and rendered with color. If DI > 0.7, it is judged as severe damage and rendered in red; if DI < 0.3, it is judged as undamaged and rendered in blue, thus realizing the visualization of the damage state of the rock mass.

[0130] Based on the principle of energy dissipation, and combined with the source information obtained from microseismic monitoring, this study analyzes the relationship between rock mass type, strength, and fracture distribution characteristics and microseismic event rate and energy rate at different stages of microseismic activity evolution; it also analyzes the relationship between energy loss from microseismic damage and changes in the physical and mechanical parameters of the rock mass, and establishes a rock mass damage criterion that considers microseismic energy dissipation.

[0131] At the same time, large-scale scientific computational feedback analysis was conducted to analyze the microseismic damage effect during the progressive failure process of the rock mass.

[0132] The specific process is as follows:

[0133] The evolution of microseismic activity is divided into four stages: quiescent, active, accelerated, mainshock, and decay. The quiescent stage represents an extremely low event rate and almost zero energy release, corresponding to an elastic state of the rock mass with no significant new damage. The active stage indicates an increasing event rate, dominated by numerous low-energy events (high b-values), corresponding to the compaction of primary fractures within the rock mass, frictional slippage, or the stable propagation of new microcracks. The accelerated stage indicates a sharp increase in the event rate, with the occurrence of even higher-energy events, highly clustered in space and time, and a continuously decreasing b-value, corresponding to localized rock mass damage, the convergence and connection of microcracks, and the formation of macroscopic fracture surfaces. The mainshock stage indicates the occurrence of one or more high-energy events, corresponding to the formation or activation of macroscopic fracture surfaces, and macroscopic damage to the rock mass (such as rockbursts and large deformations). The decay stage indicates that after the mainshock, the event rate and energy release rate gradually decrease, corresponding to a redistribution of stress reaching a new equilibrium, and a slowdown in the rate of damage.

[0134] The microseismic damage variable D_ms is constructed as follows: D_ms = Σ(E_i) / (A × σ_c² / (2E_0) × V); where Σ(E_i) is the total energy of all microseismic events accumulated within the unit volume V, σ_c is the uniaxial compressive strength of the intact rock, E_0 is the elastic modulus of the intact rock, A is the energy dissipation coefficient, which is a dimensionless empirical constant; V is the unit volume; A × σ_c² / (2E_0) × V represents the maximum theoretical elastic strain energy that the intact rock in unit volume V can store from the start of loading to complete failure under uniaxial compression conditions; Σ(E_i) represents the energy actually dissipated by the rock mass in unit volume V through microfractures under actual engineering disturbances.

[0135] The microseismic damage variable D_ms represents the proportion of energy dissipated by the rock mass due to microfractures to its maximum storeable strain energy. The higher the proportion, the more severe the damage.

[0136] The evolution equation in differential form is established as: d(D_ms) / dt=(1 / U_max)×(dE / dt), where d(D_ms) / dt represents the rate of change of the damage variable, dE / dt represents the microseismic energy release rate per unit time, and U_max is the maximum theoretical elastic strain energy.

[0137] Based on the three-dimensional geological model and the initial stress field, a finite element or finite difference model is established, and the entire model area is divided into grid cells. According to the accumulated microseismic energy Σ(E_i), an initial rate of change of damage variable D_ms is calculated for each cell and assigned to the model as a field variable.

[0138] Calculate the effective elastic modulus E_effective, where E_effective = E_0 × (1 - D_ms), and calculate the effective cohesion c_effective, where c_effective = c_0 × (1 - D_ms), where c_0 is the initial cohesion, which is the inherent bonding force between particles inside the rock.

[0139] Calculate the tangent of the effective internal friction angle tan(φ_effective), where tan(φ_effective) = tan(φ_0) × (1-ξ*D_ms), where φ_0 is the initial internal friction angle, which is the proportional relationship angle between the shear strength and normal stress of the rock when it fails under shear conditions, and ξ is the reduction factor, which takes a value <1. The reduction factor is an empirical coefficient less than 1, used to control the rate of degradation of the internal friction angle with damage.

[0140] (3) Intelligent early warning unit

[0141] Based on various advanced geological explorations, precise simulation of geological structure stress fields, and microseismic monitoring inversion results, the intelligent early warning unit 223 divides tunnel geological disaster forecasting into three stages: long-term early warning, short-term early warning, and real-time early warning.

[0142] Among them, long-term early warning involves dividing the entire tunnel into different levels of danger zones; short-term early warning forecasts are issued at a distance of 100-150m; and real-time early warning involves real-time monitoring and early warning of disasters near the construction work face.

[0143] Depending on the stage of the assessment and understanding of the unfavorable geological features ahead, the degree of danger is indicated by yellow, orange, and red, respectively. Yellow represents a moderate degree of danger, orange represents a relatively high degree of danger, and red represents an extremely high degree of danger.

[0144] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0145] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to specific implementations. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A smart early warning cloud platform for rockburst disasters in complex geological deep-buried tunnels / roadways, comprising data acquisition equipment (100) and a server (200), characterized in that: The data acquisition device (100) is connected to the server (200) via the Internet of Things (IoT) and is connected to several sensors installed in the tunnel via the IoT, which are sequentially named sensor 1, sensor 2, ..., sensor n. The server (200) is equipped with a multi-source intelligent sensing module (210) and a data intelligent analysis and early warning module (220). The multi-source intelligent sensing module (210) is used to conduct advanced geological exploration of the tunnel, establish a three-dimensional tunnel model, and obtain the rockburst susceptibility law under different geological conditions; it is also used to sense stress field changes, establish stress and strain thresholds for different rockburst levels, obtain stress concentration state and rockburst risk probability under different types of geological information, and monitor the tunnel rock mass damage state. The data intelligent analysis and early warning module (220) is used for advanced detection and precise modeling of complex geological structures, monitoring and deducing the development trend of micro-fractures, and providing intelligent early warning.

2. The intelligent early warning cloud platform for rockburst disasters in complex geological deep-buried tunnels / roadways according to claim 1, characterized in that, The multi-source intelligent sensing module (210) includes: The exploration construction unit (211) conducts advanced geological exploration of the tunnel to be excavated, records the location of adverse geological conditions characterized by large wave velocity changes, and initially marks them as rockburst risk zones; then, a tunnel model is established, and the exploration results are marked in the tunnel model; The information collection unit (212) collects the daily tunnel excavation information, marks or records it in the three-dimensional tunnel model, and compares the rock burst occurrence results under different geological conditions to obtain the rock burst susceptibility law under different geological conditions. The monitoring and sensing unit (213) senses changes in the stress field, establishes stress-strain thresholds for different rockburst levels, and obtains stress concentration states and rockburst risk probabilities under different types of geological information. The microseismic monitoring unit (214) uses microseismic monitoring methods to monitor the damage status of the tunnel rock mass in real time.

3. The intelligent early warning cloud platform for rockburst disasters in complex geological deep-buried tunnels / tunnels according to claim 2, characterized in that, The monitoring and sensing unit (213) includes stress and strain sensors arranged around the tunnel to observe the stress and strain patterns before and after rockbursts and at different construction stages and the correspondence between rockbursts of different levels, establish stress and strain thresholds for different rockburst levels, refine the risk zone or time period of rockbursts, and obtain stress concentration state and rockburst risk probability under different types of geological information in combination with geological information.

4. The intelligent early warning cloud platform for rockburst disasters in complex geological deep-buried tunnels / roadways according to claim 2, characterized in that, The microseismic monitoring unit (214) uses microseismic monitoring methods to monitor the damage state of the tunnel rock mass in real time, and includes the following steps: A mobile microseismic monitoring method was used to monitor the damage state of the tunnel rock mass in real time, obtain microseismic information before and after rockburst, establish the correspondence between microseismic parameters and rockburst, analyze the precursor information and evolution law of rockbursts of different levels, and establish early warning criteria for rockbursts of corresponding levels. Based on the established early warning criteria, before a medium- or higher-level rock eruption occurs, a text message or WeChat message is sent to the corresponding smart terminal to provide real-time dynamic intelligent early warning reminders.

5. The intelligent early warning cloud platform for rockburst disasters in complex geological deep-buried tunnels / roadways according to claim 1, characterized in that, The data intelligent analysis and early warning module (220) includes: The detection and modeling unit (221) is used for advanced detection and precise modeling of complex geological structures; The trend monitoring and simulation unit (222) is used to monitor and simulate the development trend of microfractures; The intelligent early warning unit (223) divides tunnel geological disaster forecasting into long-term early warning, short-term early warning and real-time early warning based on the results of various advanced geological explorations, precise simulation of geological structure stress fields and microseismic monitoring.

6. The intelligent early warning cloud platform for rockburst disasters in complex geological deep-buried tunnels / roadways according to claim 5, characterized in that, The working process of the detection modeling unit (221) includes the following steps: Information was collected regarding the geological and construction conditions at the site; The collected geological information is classified and summarized to infer the possible geological conditions in front of the excavation face and to establish a three-dimensional geological model. At the same time, geological information behind the excavation face is collected and processed in a timely manner. The accuracy of the established three-dimensional geological model is verified based on geological information such as the degree of fragmentation and water content of the exposed surrounding rock mass, and the established three-dimensional geological model is continuously corrected. The three-dimensional geological model was read using graphic scanning software, a three-dimensional finite element numerical model was constructed, and the three-dimensional mesh was densified by interpolation using the octree algorithm, thereby calibrating the physical and mechanical parameters of the overall model and deducing the stress field of the original rock.

7. The intelligent early warning cloud platform for rockburst disasters in complex geological deep-buried tunnels / roadways according to claim 5, characterized in that, The working process of the trend monitoring and inference unit (222) includes the following steps: 24-hour real-time monitoring of rock microfractures induced by on-site construction disturbances; collection of microseismic information of rock mass in different construction sections; analysis of the spatiotemporal intensity distribution or evolution characteristics of the collected microseismic events; assessment of the current damage state of rock mass under the influence of excavation disturbances; and inference and prediction of the orientation of unknown geological defect structures and their catastrophic evolution characteristics based on the microseismic distribution characteristics. Based on the principle of energy dissipation and combined with the source information obtained from microseismic monitoring, the relationship between rock mass type, strength and fracture distribution characteristics and microseismic event rate and energy rate in different stages of microseismic activity evolution is analyzed. The relationship between energy loss from microseismic damage and changes in the physical and mechanical parameters of rock mass was analyzed. A rock mass damage criterion considering microseismic energy dissipation was established. At the same time, large-scale scientific calculation feedback analysis was conducted to analyze the microseismic damage effect during the progressive failure process of rock mass.

Images