Safety monitoring device and safety monitoring method of roadway support system

Abstract

The invention provides a safety monitoring device and a safety monitoring method of a roadway support system, and relates to the technical field of roadway protection, and the system comprises a trend early warning cloud end, an instant early warning edge end and a monitoring end; the monitoring end comprises a plurality of monitoring points; the monitoring points comprise vertical monitoring points and horizontal monitoring points, the vertical monitoring points are arranged on the arc top of the roadway supporting system, the horizontal monitoring points are arranged on the straight wall of the first roadway supporting system, and the vertical monitoring points are used for monitoring the vertical distance from the arc top to the bottom plate of the roadway supporting system; the horizontal monitoring point is used for monitoring the horizontal distance from the straight wall of the first roadway support system to the straight wall of the second roadway support system; each monitoring point is provided with a distance sensor; the trend early warning cloud is connected with the monitoring end through the instant early warning edge end, and the trend early warning cloud is connected with the monitoring end; and the safety monitoring device performs safety monitoring on the roadway support system according to the spatial distance fluctuation quantity. And the safety monitoring real-time performance and reliability of the roadway support system are obviously improved.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel protection, and in particular to a safety monitoring device and a safety monitoring method for a tunnel support system. Background Art

[0002] The tunnel support system is a reinforcement system used to maintain the stability of the tunnel structure in underground projects such as mines and tunnels. It is usually composed of components such as steel arches, concrete linings, anchor rods (cables), metal mesh, etc. It resists ground pressure, rock deformation and external loads through mechanical support and surrounding rock reinforcement to prevent tunnel collapse or structural instability.

[0003] The geological environment in tunnels is complex and ever-changing. Due to mining stress, rock creep, and groundwater erosion, support structures are prone to gradual deformation or sudden failure. Real-time monitoring of support system parameters such as displacement and stress can accurately identify structural anomalies (such as excessive roof subsidence or accelerated sidewall convergence), providing early warning of instability risks and preventing landslides from causing casualties, equipment damage, and production interruptions.

[0004] However, existing tunnel protection system monitoring generally relies on static threshold judgment, which is easily affected by temporary disturbances and leads to false alarms and missed alarms. The lack of analytical ability for nonlinear displacement trends makes it difficult to warn of progressive instability, further leading to insufficient accuracy in tunnel support system safety monitoring. Summary of the Invention

[0005] In order to solve the technical problems in the prior art that the existing tunnel protection system monitoring generally relies on static threshold judgment, is easily affected by temporary disturbances and leads to false alarms and missed alarms, lacks the ability to analyze nonlinear displacement trends and makes it difficult to warn of progressive instability, which further leads to insufficient accuracy of tunnel support system safety monitoring, the present invention provides a tunnel support system safety monitoring device and a safety monitoring method.

[0006] The technical solutions provided by the embodiments of the present invention are as follows:

[0007] First aspect

[0008] An embodiment of the present invention provides a safety monitoring device for a tunnel support system, the system comprising: a trend warning cloud, an instant warning edge terminal, and a monitoring terminal;

[0009] The monitoring end includes multiple monitoring points;

[0010] The monitoring points include vertical monitoring points and horizontal monitoring points, wherein the vertical monitoring points are arranged at the top of the tunnel support system arc, and the horizontal monitoring points are arranged at the vertical wall of the first tunnel support system. The vertical monitoring points are used to monitor the vertical distance from the top of the arc to the bottom plate of the tunnel support system, and the horizontal monitoring points are used to monitor the horizontal distance from the vertical wall of the first tunnel support system to the vertical wall of the second tunnel support system.

[0011] Each monitoring point is equipped with a distance sensor;

[0012] The trend warning cloud is connected to the monitoring end through the instant warning edge end, and the trend warning cloud is connected to the monitoring end;

[0013] The safety monitoring device performs safety monitoring on the tunnel support system according to the spatial distance fluctuation amount, wherein the spatial distance fluctuation amount is the vertical distance fluctuation amount or the horizontal distance fluctuation amount.

[0014] Second aspect

[0015] An embodiment of the present invention provides a safety monitoring method for a tunnel support system, which is applied to the safety monitoring device of the first aspect. The method includes:

[0016] S1: Collect the real-time spatial distance fluctuation and spatial distance fluctuation history series of each monitoring point;

[0017] S2: Upload the real-time spatial distance fluctuation to the immediate warning edge end, and use the threshold method based on nonlinear energy dissipation to determine whether the real-time spatial distance fluctuation is abnormal. If so, issue an immediate warning message;

[0018] S3: Upload the historical sequence of spatial distance fluctuations to the trend warning cloud, and combine the tensor feature decomposition technology to output the predicted spatial distance fluctuation sequence;

[0019] S4: When there is a dangerous predicted spatial distance fluctuation amount greater than a preset spatial distance fluctuation amount in the predicted spatial distance fluctuation amount sequence, a trend warning information is issued;

[0020] S5: Output the immediate warning information and trend warning information as the safety monitoring results of the tunnel support system, and return to step S1.

[0021] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0022] In the present invention, the safety monitoring device integrates edge real-time analysis and cloud trend prediction through a dual-modal early warning mechanism. Based on the dynamic threshold model of the nonlinear energy density function, it effectively distinguishes temporary disturbances from real dangers, reduces the false alarm rate, and improves the accuracy of safety monitoring. In addition, the spatiotemporal tensor decomposition technology is used to analyze the curvature and mutation characteristics of the displacement sequence to achieve trend warning, which can identify the risk of progressive instability in advance. The vertical and horizontal dual-dimensional high-density sensor network realizes multi-angle safety monitoring of the tunnel support system. This solution combines the high-speed response capability of the edge with the powerful deep data trend analysis capability of the cloud to form a full-cycle prevention and control system from rapid instantaneous anomaly capture to long-term deformation prediction, significantly improving the reliability of safety monitoring of the tunnel support system under complex geological conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A schematic structural diagram of a safety monitoring device for a tunnel support system provided by an embodiment of the present invention;

[0025] Figure 2 A schematic cross-sectional view of a safety monitoring device for a tunnel support system provided by an embodiment of the present invention;

[0026] Figure 3 A schematic cross-sectional view of a safety monitoring device for another tunnel support system provided by an embodiment of the present invention;

[0027] Figure 4 A schematic structural diagram of another safety monitoring device for a tunnel support system provided by an embodiment of the present invention;

[0028] Figure 5 A schematic flow chart of a safety monitoring method for a tunnel support system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0030] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0031] In the embodiments of the present invention, the terms "image" and "picture" may be used interchangeably. It should be noted that, when the distinction between them is not emphasized, their intended meanings are the same. The terms "of," "corresponding," and "corresponding" may be used interchangeably. It should be noted that, when the distinction between them is not emphasized, their intended meanings are the same.

[0032] In the embodiments of the present invention, sometimes a subscript such as W1 may be mistakenly written as a non-subscript form such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0033] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0034] Reference Manual Figure 1 , shows a structural schematic diagram of a safety monitoring device for a tunnel support system provided by an embodiment of the present invention.

[0035] Figure 1 The safety monitoring device's architecture is demonstrated to consist of three main components: a trend warning cloud, an immediate warning edge, and a monitoring end. The trend warning cloud is responsible for long-term risk analysis and data processing. The immediate warning edge is used to quickly respond to real-time data from the field and issue warnings. The monitoring end includes vertical and horizontal monitoring points. Sensors collect real-time spatial distance changes in the tunnel support system to monitor structural safety. This multi-layered monitoring and early warning mechanism can accurately and timely improve the safety of the tunnel support system.

[0036] Reference Manual Figure 2 , showing a schematic cross-sectional structure diagram of a safety monitoring device for a tunnel support system provided by an embodiment of the present invention.

[0037] Figure 2 The cross-sectional layout of the tunnel with the arch structure is shown, in which a vertical monitoring point is set on the top to monitor the vertical deformation from the arch to the bottom plate, and multiple horizontal monitoring points are set on the straight walls on both sides to measure the horizontal distance changes between the walls on both sides. The overall structure realizes comprehensive monitoring of the tunnel space deformation through vertical and horizontal point layout.

[0038] Reference Manual Figure 3 , shows a schematic cross-sectional structure diagram of another safety monitoring device for a tunnel support system provided by an embodiment of the present invention.

[0039] Figure 3 A schematic diagram of the side cross-section of the tunnel support system is presented, showing the relative positions of the tunnel interior and the support structure, including key components such as the arch, vertical walls, and floor. The structure clearly shows that the first and second vertical walls are located on either side of the tunnel, with the top of the arched structure.

[0040] Reference Manual Figure 4 , shows a schematic structural diagram of a safety monitoring device for another tunnel support system provided by an embodiment of the present invention.

[0041] Figure 4A schematic diagram of a safety monitoring device for a tunnel support system is shown, specifically the structural layout of the safety monitoring device for a fully arched tunnel support system, in which multiple vertical monitoring points are arranged on the tunnel arch, and the changes in the spatial distance between the arch and the bottom plate of the support system are monitored in real time through vertical ranging. This is used to determine whether there are risks such as sinking and collapse, thereby improving the dynamic monitoring capability of the tunnel structure stability.

[0042] An embodiment of the present invention provides a safety monitoring device for a tunnel support system, the system comprising: a trend warning cloud, an immediate warning edge terminal and a monitoring terminal. The monitoring terminal comprises a plurality of monitoring points. The monitoring points comprise vertical monitoring points and horizontal monitoring points, wherein the vertical monitoring points are arranged at the top of the tunnel support system arc, and the horizontal monitoring points are arranged at the vertical wall of the first tunnel support system, wherein the vertical monitoring points are used to monitor the vertical distance from the top of the arc to the bottom plate of the tunnel support system, and the horizontal monitoring points are used to monitor the horizontal distance from the vertical wall of the first tunnel support system to the vertical wall of the second tunnel support system. Each monitoring point is provided with a distance sensor. The trend warning cloud is connected to the monitoring terminal via the immediate warning edge terminal, and the trend warning cloud is connected to the monitoring terminal. The safety monitoring device performs safety monitoring on the tunnel support system according to the spatial distance fluctuation amount, wherein the spatial distance fluctuation amount is the vertical distance fluctuation amount or the horizontal distance fluctuation amount.

[0043] The trend warning cloud, a computing platform located on a cloud server, processes long-term data and predicts trend-based risks (such as slow deformation and potential instability). The immediate warning edge, located on edge devices close to the monitoring site, features fast computing capabilities and processes real-time data, making immediate safety assessments (such as mutation detection and identification of abnormal fluctuations). It issues immediate warnings upon detecting risks. The monitoring end, comprised of multiple monitoring points deployed throughout the tunnel structure, serves as the system's "perception layer." Each monitoring point is equipped with a distance sensor, which collects real-time data on spatial structural changes. Vertical monitoring points, installed at the tunnel's arch, measure vertical distance changes from the arch to the floor, indicating potential tunnel subsidence or roof collapse. Horizontal monitoring points, installed between tunnel walls, measure horizontal distance changes between the two walls, indicating potential lateral risks due to compression, contraction, or deformation. Distance sensors, located at each monitoring point, can accurately record spatial changes between support structures.

[0044] It should be noted that the tunnel support system safety monitoring device uses multi-point ranging sensors arranged vertically and horizontally to perceive the spatial deformation of the tunnel structure in real time. Combined with rapid edge warnings and cloud-based trend analysis, it enables comprehensive monitoring of sudden displacements and slowly evolving instabilities. Its high timeliness and multi-scale feature analysis capabilities significantly improve warning accuracy and response efficiency.

[0045] In practical application, this safety monitoring device deploys vertical and horizontal monitoring points along the arches and vertical walls of the tunnel structure. It uses distance sensors such as laser, infrared, and ultrasonic sensors to collect real-time vertical and horizontal distance data from the tunnel's spatial structure. The edge device rapidly analyzes this data, identifies sudden abnormal changes, and issues immediate warnings. Historical fluctuation data is also uploaded to the cloud, where trend analysis algorithms are used to predict potential instability risks, enabling efficient, safe, and dynamic monitoring and early warning of the tunnel support system.

[0046] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0047] In the present invention, the safety monitoring device integrates edge real-time analysis and cloud trend prediction through a dual-modal early warning mechanism. Based on the dynamic threshold model of the nonlinear energy density function, it effectively distinguishes temporary disturbances from real dangers, reduces the false alarm rate, and improves the accuracy of safety monitoring. In addition, the spatiotemporal tensor decomposition technology is used to analyze the curvature and mutation characteristics of the displacement sequence to achieve trend warning, which can identify the risk of progressive instability in advance. The vertical and horizontal dual-dimensional high-density sensor network realizes multi-angle safety monitoring of the tunnel support system. This solution combines the high-speed response capability of the edge with the powerful deep data trend analysis capability of the cloud to form a full-cycle prevention and control system from rapid instantaneous anomaly capture to long-term deformation prediction, significantly improving the reliability of safety monitoring of the tunnel support system under complex geological conditions.

[0048] In a possible implementation, the distance sensor includes an ultrasonic distance sensor, an infrared distance sensor, and a laser distance sensor.

[0049] It is understandable that distance sensors can be ultrasonic, infrared or laser ranging sensors. Different types of sensors can be selected and deployed according to the tunnel environment. They have the characteristics of fast response speed, high ranging accuracy, and strong adaptability. They can realize efficient and stable real-time monitoring of spatial distance changes at key positions of the tunnel support system.

[0050] Reference Manual Figure 5 , which shows a flow chart of a safety monitoring method for a tunnel support system provided by an embodiment of the present invention.

[0051] The present invention also provides a safety monitoring method for a tunnel support system, which is applied to the above-mentioned safety monitoring device for the tunnel support system. The method comprises:

[0052] S1: Collect the real-time spatial distance fluctuation and spatial distance fluctuation history series of each monitoring point.

[0053] Real-time spatial distance fluctuation refers to the spatial distance change value collected at a specific moment, such as the change in distance from the vault to the floor or between the two vertical walls measured at a specific monitoring point. This value reflects the immediate deformation of the structure. A historical sequence of spatial distance fluctuation refers to a sequence of spatial distance fluctuation data continuously recorded over a period of time. This sequence is used to analyze the deformation trend or inertia of a structure over time. For example, a record of vertical / horizontal displacement changes over the past N minutes or hours. By simultaneously acquiring real-time spatial distance fluctuation and its historical sequence, comprehensive data support is provided for subsequent emergency warnings and trend forecasts, balancing current status with evolving trends and improving monitoring accuracy.

[0054] S2: Upload the real-time spatial distance fluctuation to the immediate warning edge end, and use the threshold method based on nonlinear energy dissipation to determine whether the real-time spatial distance fluctuation is abnormal. If so, issue an immediate warning message.

[0055] Nonlinear energy dissipation refers to the situation where, when a structure or system is disturbed, the input energy is not fully stored in the system or elastically recovered, but rather dissipated in a certain manner due to the presence of nonlinear response mechanisms within it. The threshold method based on nonlinear energy dissipation describes the conversion of real-time spatial distance fluctuations into energy dissipation characteristics. Based on historical statistics and physical models, a nonlinear dissipation threshold is then set to identify whether the system is in a dangerous state.

[0056] It's important to note that by uploading real-time monitoring data to the edge and performing intelligent analysis based on a nonlinear energy dissipation threshold method, we can effectively identify dramatic displacement fluctuations caused by sudden structural anomalies. Compared to traditional fixed threshold methods, this approach not only requires no historical training data, offers faster response times, and exhibits stronger anti-interference capabilities, significantly reducing false positives and missed alerts, ensuring real-time and accurate early warnings.

[0057] In a possible implementation, the immediate warning information includes sound warning information and visual warning information regarding abnormal real-time spatial distance fluctuation.

[0058] It is understandable that immediate warning information not only issues alarms through sound, but also provides visual prompts through graphical interfaces or signal lights, etc., which helps on-site staff to intuitively and quickly identify the location and degree of risks in the first time, thereby improving emergency response efficiency.

[0059] In a possible implementation, S2 specifically includes:

[0060] S201: Convert the real-time spatial distance fluctuation into equivalent energy density to obtain a real-time energy density function value related to nonlinear energy dissipation.

[0061] The calculation method of the real-time energy density function value is as follows:

[0062]

[0063] Among them, E t represents the real-time energy density function value at time t, t0 represents the starting time of integration, τ represents the integral variable, Δd represents the real-time space distance fluctuation, Δd(τ) represents the real-time space distance fluctuation when the integral variable is τ, β represents the positive coefficient for amplifying the sudden change of the real-time space distance fluctuation, and e represents a natural constant.

[0064] Among them, equivalent energy density refers to the quantitative expression of the "response behavior" of the structure due to deformation, disturbance, etc. in the form of "energy" within unit time or unit area. It converts the original spatial distance fluctuations (such as displacement or deformation) into energy form, which facilitates the capture of abnormal states or mutation characteristics from a physical perspective. This energy density is calculated by squaring the second-order derivative of the spatial distance fluctuation (i.e., acceleration) and combining it with an exponentially decayed weighted integral. It has mutation sensitivity and small disturbance suppression, and can more realistically reflect the nonlinear response intensity of the fluctuation.

[0065] By converting real-time spatial distance fluctuations into equivalent energy density, it can not only reveal the dynamic characteristics behind structural deformation, but also effectively identify short-term strong mutation behaviors. Compared with traditional displacement monitoring, this method is more sensitive to abnormal changes and has good suppression capabilities for small-amplitude disturbances, thereby improving the accuracy of early warning and the stability of judgment.

[0066] S202: Calculating a warning boundary surface function related to the energy density function value in the Hilbert phase space.

[0067] The specific warning boundary surface function is:

[0068]

[0069] Where E represents the energy density function value, represents the rate of change of the energy density function value, Indicates that E and The relevant warning boundary surface function value, Q represents the covariance matrix of the historical energy density function value, exp represents the natural exponential function, Indicates that E and A two-dimensional column vector of Denote the weighted matrix as Q -1 The weighted norm of , Φ(t) represents the warning threshold at time t, N represents the number of abnormal historical spatial distance fluctuations recorded, The maximum Lyapunov exponent representing the k-th abnormal historical spatial distance fluctuation, t kIt represents the time when the kth abnormal historical spatial distance fluctuation occurs, and L represents the memory length of the abnormal historical spatial distance fluctuation.

[0070] Among them, the Hilbert phase space is a high-dimensional space used mathematically to describe the evolution of system states. In time series analysis, it is often used to map the original one-dimensional time series into a multi-dimensional phasor trajectory, thereby capturing the changing trend and potential nonlinear structure of the system's internal state. The early warning boundary surface function is a dynamic discriminant function used to determine whether the current system energy state has crossed the safety boundary. By mapping the energy density and its rate of change to the Hilbert phase space and combining it with the boundary surface function constructed based on historical abnormal behaviors, it is dynamically evaluated whether the current state has crossed the boundary. Compared with traditional static discrimination methods, it can more accurately reflect the degree of deviation between the current and historical states of the system, has stronger anomaly recognition capabilities, time series adaptability, and physical rationality, and significantly improves the sensitivity and reliability of early warnings.

[0071] S203: When the warning boundary surface function value corresponding to the real-time energy density function value satisfies the joint threshold condition, issuing an immediate warning message, wherein the joint threshold condition includes a boundary threshold condition and a fluctuation speed threshold condition.

[0072] The formula form of the joint threshold condition is as follows:

[0073]

[0074] Among them, E t and They represent the energy density function value at time t and the rate of change of the energy density function value at time t, respectively. Indicates that E t and The relevant real-time energy density function value corresponds to the warning boundary surface function value, and ζ represents the preset fluctuation speed threshold.

[0075] It should be noted that those skilled in the art can set the preset fluctuation speed according to actual needs, and the present invention does not limit this.

[0076] Specifically, the process converts the real-time spatial distance fluctuation into an energy density function value, uses its second-order derivative to reflect acceleration changes, and achieves a sensitive response to large-amplitude mutations through exponential decay, capturing the nonlinear response characteristics of the structure. Subsequently, a warning boundary surface function related to energy density and its rate of change is constructed in the Hilbert phase space. By comparing historical abnormal behaviors, a dynamic threshold function is constructed to achieve more accurate safety judgments. This method effectively combines the dynamic change trend with the historical statistical behavior of the system, has stronger mutation recognition capabilities and anti-interference capabilities, can significantly reduce false alarms and missed alarms, and improve the scientific nature and real-time nature of the warning response.

[0077] In a possible implementation, after S2 and before S3, the process further includes:

[0078] The historical series of spatial distance fluctuations are preprocessed, where the preprocessing includes data cleaning and time alignment.

[0079] It is understandable that by performing data cleaning and time alignment on the historical series of spatial distance fluctuations, outliers, missing values, and asynchronous data can be effectively eliminated, ensuring the accuracy and stability of subsequent tensor construction and trend prediction, thereby improving the reliability and analysis effect of the overall monitoring system.

[0080] S3: Upload the historical sequence of spatial distance fluctuations to the trend warning cloud, and combine the tensor feature decomposition technology to output the predicted spatial distance fluctuation sequence.

[0081] Tensor eigendecomposition is a mathematical method for pattern extraction and structure recognition from high-order data (such as three-dimensional data). It constructs a three-dimensional tensor structure based on the historical sequence of spatial distance fluctuations in the roadway. It extracts the dominant dynamic features (such as change trends and inertial directions) and uses them to predict future displacement changes.

[0082] It's important to note that by constructing historical spatial distance fluctuation data into a tensor and extracting key features for trend prediction, this method effectively overcomes the limitations of traditional threshold methods in identifying slowly evolving risks. This method not only enables early detection of structural displacement trends but also possesses high-dimensional modeling capabilities for local dynamic behavior, significantly improving the accuracy and advance warning of potential instability in tunnel support systems.

[0083] In a possible implementation, S3 specifically includes:

[0084] S301: Construct a tensor describing the local dynamic behavior of the spatial distance fluctuation quantity based on the spatial distance fluctuation quantity corresponding to the moment triple in the historical sequence of the spatial distance fluctuation quantity, wherein the moment triple includes the first moment, the second moment and the third moment belonging to the adjacent relationship.

[0085] The tensor formula is as follows:

[0086]

[0087] Among them, i and j represent the tensor row index and tensor column index respectively, M ij (t0) represents the tensor i row and j column element describing the local dynamic behavior of the spatial distance fluctuation at time t0, t0-1, t0, t0+1 represent the first moment, the second moment, and the third moment respectively, m represents the reference time step in the historical sequence of the spatial distance fluctuation, s krepresents the spatial distance fluctuation amount at time k of the historical sequence of spatial distance fluctuation amount, Δ 2 s k It represents the second-order difference term that measures the curvature of the spatial distance fluctuation trend, Δ 3 s k It represents the third-order difference term that measures the degree of mutation in the trend of spatial distance fluctuation, and η represents the attenuation factor that controls the intensity of mutual influence between different moments in the tensor.

[0088] It should be noted that this process constructs a local tensor by extracting the spatial distance fluctuations of three adjacent moments, comprehensively considering the trend curvature reflected by the second-order difference and the mutation characteristics reflected by the third-order difference, and at the same time introducing an exponential decay factor to suppress interference at distant moments, thereby accurately expressing the dynamic behavior characteristics of the time series data within the local time window, and being able to capture the subtle and critical structural evolution trends of the tunnel support system, and enhance the sensitivity to potential deformation risks and modeling expression capabilities.

[0089] S302: Find the maximum eigenvector and maximum eigenvalue of the tensor.

[0090] In a possible implementation, S302 specifically includes:

[0091] S3021: Solve the determinant of the tensor and obtain the maximum eigenvalue.

[0092] The determinant is specifically:

[0093] det(M ij (t0)-λ max I)=0

[0094] Among them, det represents the determinant symbol, I represents the identity matrix, λ max represents the maximum eigenvalue.

[0095] S3022: Substitute the maximum eigenvalue into the homogeneous equation about the tensor and solve it to obtain the maximum eigenvector.

[0096] The homogeneous equation is specifically:

[0097] (M ij (t0)-λ max I)v max =0

[0098] Among them, v max represents the largest eigenvector.

[0099] It should be noted that this process first determines the maximum eigenvalue by solving the determinant of the difference between the tensor and the identity matrix. This is then substituted into a homogeneous linear system of equations to calculate the corresponding maximum eigenvector, which is used to extract the tensor's principal direction features. This effectively identifies the most representative dynamic patterns in structural changes, avoids interference from local fluctuations, and provides a stable and accurate feature foundation for subsequent trend predictions, improving the reliability of overall predictions.

[0100] S303: Based on the maximum eigenvalue and the maximum eigenvector, solve the second-order difference prediction term that captures the local dynamic behavior of the spatial distance fluctuation quantity.

[0101] The specific solution formula is:

[0102]

[0103] Among them, p represents the prediction step size, sgn represents the sign function, Indicates v max The transpose of They represent the second-order difference terms at the first moment, i.e., time t0-1, and the second moment, i.e., time t0, in the history sequence of spatial distance fluctuations, respectively. represents the second-order difference term at the third moment, i.e., t0+1, represents the second-order difference prediction term for the next p steps.

[0104] It should be noted that this process uses the maximum eigenvalue and eigenvector extracted from the tensor decomposition to perform weighted operations on the second-order difference terms of the three historical moments, and combines the symbolic function to predict the second-order difference trend of the next p steps, reflecting the main dynamic direction of the structural change. It can effectively extract the dominant mode in the local change, avoid noise interference, and enhance the prediction stability and foresight of the deformation trend of the tunnel support system.

[0105] S304: Perform reverse integration on the second-order difference prediction term to construct a prediction space distance fluctuation sequence.

[0106] The reverse integration formula is:

[0107]

[0108] in, Indicates the fluctuation of the predicted spatial distance at time k+p, i indicates the prediction step index, represents the second-order difference prediction term for the next j steps, Δs k Represents the fluctuation change of the spatial distance between time k and the adjacent time.

[0109] Specifically, the process first extracts the spatial distance fluctuations between three adjacent moments in the historical sequence, constructing a tensor that contains trend curvature and mutation characteristics. The tensor's maximum eigenvalue and eigenvector are then calculated to extract the main direction of local dynamic behavior. Future second-order difference terms are then predicted based on this main characteristic direction, and the future spatial distance fluctuation sequence is restored through inverse integration. This method not only accounts for the local inertia and nonlinear dynamics of structural evolution but also possesses strong trend capture and disturbance suppression capabilities, significantly improving the accuracy and foresight of predictions of potential instability risks.

[0110] S4: When there is a dangerous predicted spatial distance fluctuation amount greater than a preset spatial distance fluctuation amount in the predicted spatial distance fluctuation amount sequence, a trend warning message is issued.

[0111] It should be noted that those skilled in the art can set the size of the preset spatial distance fluctuation amount according to actual needs, and the present invention does not limit this.

[0112] It's important to note that by evaluating the predicted spatial distance fluctuation sequence, if any dangerous values ​​exceeding a preset safety threshold are detected, a trend warning is issued in advance, effectively identifying potential displacement hazards that have not yet occurred but may continue to develop. This method significantly improves the early warning time, overcoming the shortcomings of traditional methods that rely solely on real-time data and cannot capture progressive risks, and enhancing the ability to ensure the long-term stability of tunnel structures.

[0113] In a possible implementation, the trend warning information includes the dangerous moment corresponding to the dangerous predicted spatial distance fluctuation amount in the predicted spatial distance fluctuation amount sequence.

[0114] It is understandable that this trend warning information not only points out the possible fluctuations in dangerous spatial distances in the future, but also clearly gives the specific dangerous moments corresponding to the abnormal prediction values ​​in the time series, which helps to deploy safety precautions in advance and improve the operability and timeliness of the warning.

[0115] S5: Output the immediate warning information and trend warning information as the safety monitoring results of the tunnel support system, and return to step S1.

[0116] In a possible implementation manner, after S5, the method further includes:

[0117] Update the spatial distance fluctuation history sequence at preset intervals.

[0118] It should be noted that those skilled in the art can set the preset duration according to actual needs, and the present invention does not limit this.

[0119] It can be understood that by setting fixed time intervals to periodically update the historical series of spatial distance fluctuations, it is possible to ensure that the historical data used remains up to date, thereby improving the real-time and accuracy of trend forecasts and early warning judgments.

[0120] In actual application, the tunnel support system safety monitoring method first collects real-time and historical spatial distance fluctuations, taking into account both instantaneous response and evolutionary trends. A boundary threshold method based on nonlinear energy dissipation is then used for rapid anomaly identification, improving the sensitivity and robustness of immediate warnings. Tensor eigendecomposition methods are then used to conduct trend predictions, identifying slowly changing or latent instability risks. Trend warnings are then issued at specific time points to enhance the operability of warnings. The entire process combines physical modeling and data analysis, offering advantages such as no training required, high anti-interference capabilities, strong real-time performance, and strong predictive capabilities, significantly improving the accuracy and timeliness of safety monitoring of tunnel support systems.

[0121] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0122] In the present invention, the safety monitoring device integrates edge real-time analysis and cloud trend prediction through a dual-modal early warning mechanism. Based on the dynamic threshold model of the nonlinear energy density function, it effectively distinguishes temporary disturbances from real dangers, reduces the false alarm rate, and improves the accuracy of safety monitoring. In addition, the spatiotemporal tensor decomposition technology is used to analyze the curvature and mutation characteristics of the displacement sequence to achieve trend warning, which can identify the risk of progressive instability in advance. The vertical and horizontal dual-dimensional high-density sensor network realizes multi-angle safety monitoring of the tunnel support system. This solution combines the high-speed response capability of the edge with the powerful deep data trend analysis capability of the cloud to form a full-cycle prevention and control system from rapid instantaneous anomaly capture to long-term deformation prediction, significantly improving the reliability of safety monitoring of the tunnel support system under complex geological conditions.

[0123] It should be understood that the processor in the embodiments of the present invention may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0124] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus RAM (DR RAM).

[0125] The above embodiments can be implemented in whole or in part through software, hardware (such as circuits), firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired method (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage system such as a server or data center that contains a collection of one or more available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, or tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0126] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0127] In this disclosure, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0128] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0129] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0130] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0131] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0132] The units described as separate components may or may not be physically separate, and 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 these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0133] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0134] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer system (which can be a personal computer, server, or network system, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0135] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

[0136] There are a few points to note:

[0137] (1) The drawings of the embodiments of the present invention only relate to the structures related to the embodiments of the present invention. Other structures may refer to conventional designs.

[0138] (2) For the sake of clarity, the thickness of layers or regions in the drawings used to describe the embodiments of the present invention are exaggerated or reduced, that is, these drawings are not drawn to scale. It is understood that when an element such as a layer, film, region, or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or intervening elements may be present.

[0139] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to form new embodiments.

[0140] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A safety monitoring device for a tunnel support system, characterized in that: include: Trend warning cloud, real-time warning edge and monitoring end; The monitoring end includes a plurality of monitoring points; The monitoring points include vertical monitoring points and horizontal monitoring points, wherein the vertical monitoring points are arranged at the top of the tunnel support system arc, and the horizontal monitoring points are arranged at the vertical wall of the first tunnel support system, wherein the vertical monitoring points are used to monitor the vertical distance from the top of the arc to the bottom plate of the tunnel support system, and the horizontal monitoring points are used to monitor the horizontal distance from the vertical wall of the first tunnel support system to the vertical wall of the second tunnel support system; Each of the monitoring points is provided with a distance sensor; The trend warning cloud is connected to the monitoring terminal via the instant warning edge terminal, and the trend warning cloud is connected to the monitoring terminal; The safety monitoring device performs safety monitoring on the tunnel support system according to the spatial distance fluctuation amount, wherein the spatial distance fluctuation amount is the vertical distance fluctuation amount or the horizontal distance fluctuation amount.

2. The safety monitoring device for the tunnel support system according to claim 1, characterized in that: The distance sensor includes an ultrasonic distance sensor, an infrared distance sensor and a laser distance sensor.

3. A safety monitoring method for a tunnel support system, characterized in that: The safety monitoring device according to any one of claims 1 to 2, wherein the method comprises: S1: collecting the real-time spatial distance fluctuation and spatial distance fluctuation history sequence of each monitoring point; S2: uploading the real-time spatial distance fluctuation to the immediate warning edge terminal, combining a threshold method based on nonlinear energy dissipation to determine whether the real-time spatial distance fluctuation is abnormal, and if so, issuing an immediate warning message; S3: uploading the spatial distance fluctuation history sequence to the trend warning cloud, and outputting the predicted spatial distance fluctuation sequence in combination with tensor feature decomposition technology; S4: issuing trend warning information when there is a dangerous predicted spatial distance fluctuation amount greater than a preset spatial distance fluctuation amount in the predicted spatial distance fluctuation amount sequence; S5: Output the immediate warning information and the trend warning information as the safety monitoring result of the tunnel support system, and return to step S1.

4. The safety monitoring method for a tunnel support system according to claim 3, characterized in that: The instant warning information includes sound warning information and visual warning information about abnormal real-time spatial distance fluctuation.

5. The safety monitoring method for a tunnel support system according to claim 3, characterized in that: The S2 specifically includes: S201: Converting the real-time spatial distance fluctuation into equivalent energy density to obtain a real-time energy density function value related to nonlinear energy dissipation; S202: Calculating a warning boundary surface function related to the energy density function value in the Hilbert phase space; S203: When the warning boundary surface function value corresponding to the real-time energy density function value satisfies the joint threshold condition, the immediate warning information is issued, wherein the joint threshold condition includes a boundary threshold condition and a fluctuation speed threshold condition.

6. The safety monitoring method for a tunnel support system according to claim 3, characterized in that: After S2 and before S3, the method further includes: The spatial distance fluctuation history sequence is preprocessed, wherein the preprocessing includes data cleaning and time alignment.

7. The safety monitoring method for a tunnel support system according to claim 3, characterized in that: The S3 specifically includes: S301: Constructing a tensor describing the local dynamic behavior of the spatial distance fluctuation amount based on the spatial distance fluctuation amount corresponding to the time triple in the spatial distance fluctuation amount history sequence, wherein the time triple includes a first time, a second time, and a third time that are in a neighboring relationship; S302: Calculate the maximum eigenvector and maximum eigenvalue of the tensor; S303: Based on the maximum eigenvalue and the maximum eigenvector, solving a second-order difference prediction term that captures the local dynamic behavior of the spatial distance fluctuation quantity; S304: Perform reverse integration on the second-order difference prediction item to construct the prediction space distance fluctuation sequence.

8. The safety monitoring method for a tunnel support system according to claim 7, characterized in that: The S302 specifically includes: S3021: Solve the determinant of the tensor to obtain the maximum eigenvalue; S3022: Substitute the maximum eigenvalue into the homogeneous equation about the tensor and solve to obtain the maximum eigenvector.

9. The safety monitoring method for a tunnel support system according to claim 3, characterized in that: The trend warning information includes the dangerous moment corresponding to the dangerous predicted spatial distance fluctuation amount in the predicted spatial distance fluctuation amount sequence.

10. The safety monitoring method for a tunnel support system according to claim 3, characterized in that: After S5, the method further includes: The spatial distance fluctuation amount history sequence is updated at intervals of a preset time length.

Images