Intelligent monitoring and support system and method for surrounding rock stability in tunnel construction

Abstract

This invention discloses an intelligent monitoring and support system and method for surrounding rock stability in tunnel construction, aiming to solve the problems of data silos, multiple solutions in inversion, inaccurate early warning, and delayed support in existing technologies. The system includes a multi-source collaborative sensing module, a dynamic coupling inversion module, a probabilistic early warning module, an adaptive support module, and a data transmission module. The method achieves closed-loop management based on this system. The multi-source collaborative sensing module collects multi-physics field data, the dynamic coupling inversion module performs three-dimensional joint inversion, the probabilistic early warning module quantifies risk probabilities, and the adaptive support module dynamically adjusts support parameters. This invention integrates monitoring, inversion, early warning, and support, improving the accuracy of surrounding rock condition assessment and the reliability of risk early warning, achieving matching between support and surrounding rock condition, reducing construction risks, and balancing safety and economy. It is suitable for tunnel construction under complex geological conditions.

Description

Technical Field

[0001] This invention relates to the field of tunnel construction, specifically to an intelligent monitoring and support system and method for surrounding rock stability in tunnel construction. Background Technology

[0002] During tunnel construction, the stability of the surrounding rock directly affects construction safety and project quality, making it a core focus of tunnel construction management. Currently, existing tunnel surrounding rock stability monitoring and support technologies still have many shortcomings and are difficult to adapt to the construction needs under complex geological conditions. Existing monitoring technologies mostly employ single physical field monitoring methods, and the coordinate systems and sampling schemes of various monitoring devices are inconsistent, resulting in independent data silos that cannot be effectively integrated and fail to comprehensively reflect the true state of the surrounding rock. Furthermore, surrounding rock parameter inversion often relies on single physical field data, leading to highly variable inversion results with insufficient accuracy, failing to provide reliable support for risk early warning. In addition, existing early warning methods are mostly qualitative level warnings, unable to quantify risk probabilities, and prone to missed or false alarms. Support operations often rely heavily on the experience of construction workers and use fixed support parameters, which cannot be adjusted in real time according to the dynamic changes of the surrounding rock. This can easily lead to a mismatch between the support force and the stress of the surrounding rock, either causing stress concentration failure or resulting in excessive support and waste. Furthermore, the monitoring and support processes are disconnected, making it impossible to form a closed-loop management system, which seriously affects the safety and economy of tunnel construction. Therefore, the development of intelligent monitoring and support systems and methods for surrounding rock stability in tunnel construction that can solve the above problems has become an urgent need in the field of tunnel construction technology. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to overcome the defects of the above-mentioned technologies and provide an intelligent monitoring and support system and method for surrounding rock stability in tunnel construction.

[0004] To address the aforementioned technical problems, the present invention provides a technical solution: an intelligent monitoring and support system and method for surrounding rock stability in tunnel construction. The intelligent monitoring and support system for surrounding rock stability in tunnel construction includes a multi-source collaborative sensing module, a dynamic coupling inversion module, a probabilistic early warning module, an adaptive support module, and a data transmission module. The multi-source collaborative sensing module integrates four monitoring technologies: distributed fiber optic sensing, acoustic emission monitoring, high-precision ground-penetrating radar, and drilling parameter acquisition. It employs a unified spatiotemporal reference calibration technique to address the inconsistency between different sensor coordinate systems and sampling schemes, simultaneously acquiring surrounding rock strain, temperature, acoustic emission energy, wave velocity, resistivity, and drilling parameters. The data transmission module transmits the monitoring data acquired by the multi-source collaborative sensing module to the dynamic coupling inversion module. The dynamic coupling inversion module performs a three-dimensional joint inversion based on the monitoring data and updates the surrounding rock physical property field and seepage evolution model. The probabilistic early warning module generates risk levels and probabilities based on the inversion results and triggers early warning signals. The adaptive support module receives the early warning signals and adjusts support parameters according to the real-time state of the surrounding rock, achieving closed-loop collaboration between monitoring and support.

[0005] As an improvement, the multi-source collaborative sensing module includes several distributed fiber optic sensors, acoustic emission sensors, ground-penetrating radar probes, and drilling parameter acquisition devices. All sensors and acquisition devices are calibrated with a unified spatiotemporal reference to ensure the spatiotemporal consistency of the acquired data and avoid the data silo effect.

[0006] As an improvement, the dynamic coupling inversion module adopts an original three-dimensional joint inversion algorithm of physical property parameters-seepage evolution-stress state, introduces strain rate and acoustic emission energy as dynamic constraints, constructs a dynamic evolution model of surrounding rock permeability, and explicitly describes the abrupt change behavior of seepage channels during the rapid connection of microfractures.

[0007] As an improvement, the probabilistic early warning module explicitly maps model uncertainty to a risk probability function. Combined with an anomaly detection model trained by machine learning algorithms, it constructs a multi-level risk probability early warning system, which can dynamically correct the risk probability based on the distribution of surrounding rock physical parameters and the degree of seepage evolution.

[0008] As an improvement, the adaptive support module includes an advanced small-diameter pipe grouting unit, a telescopic anchor bolt placement unit, a flexible shotcrete pouring unit, and an intelligent actuator. The intelligent actuator is used to control the three support units in a coordinated manner, so as to realize the real-time dynamic adjustment of support parameters.

[0009] A method for intelligent monitoring and support of surrounding rock stability for tunnel construction includes the following steps: Before construction, all sensors and acquisition devices in the multi-source collaborative sensing module are uniformly calibrated and deployed, a three-dimensional geological model of the tunnel is constructed, and historical engineering data is input to train the inversion algorithm of the dynamic coupling inversion module and the early warning algorithm of the probabilistic early warning module; During construction, multi-physical field data of the surrounding rock are synchronously collected through the multi-source collaborative sensing module and transmitted to the dynamic coupling inversion module through the data transmission module. The dynamic coupling inversion module performs three-dimensional joint inversion and updates the surrounding rock physical property parameter field and seepage evolution model in real time to ensure the synergy between monitoring data and the inversion process.

[0010] As an improvement, a risk warning step is also included: the probabilistic warning module receives the surrounding rock physical property parameter field and seepage evolution model data output by the dynamic coupling inversion module, identifies abnormal surrounding rock conditions through the anomaly detection model, maps the model uncertainty into risk probability, generates multiple risk levels and corresponding probabilities, and triggers warning signals of the corresponding level.

[0011] As an improvement, an adaptive support step is also included: the adaptive support module receives the early warning signal output by the probabilistic early warning module and the real-time status data of the surrounding rock, and controls the advanced small pipe grouting unit, the telescopic anchor bolt placement unit, and the flexible shotcrete pouring unit through the linkage of the intelligent actuator, adjusts the support parameters and executes the support operation.

[0012] As an improvement, in the adaptive support step, the support parameters are adjusted based on the deformation rate of the surrounding rock, the stress state, and the degree of seepage evolution to achieve a dynamic balance between the support force and the stress of the surrounding rock, thereby avoiding stress concentration damage caused by rigid support.

[0013] As an improvement, a dynamic iterative optimization step is also included: continuously collecting response data of the surrounding rock after support, feeding the response data back to the dynamic coupling inversion module and the adaptive support module, optimizing the inversion algorithm parameters and support strategy, and realizing dynamic iteration throughout the entire construction process.

[0014] The advantages of this invention compared to existing technologies are as follows: This technical solution effectively solves the problem of isolated monitoring data in existing tunnel construction. By integrating multiple monitoring technologies through a multi-source collaborative sensing module, it achieves synchronous acquisition and fusion of various monitoring data, providing accurate data support for subsequent work. Simultaneously, it overcomes the problem of multiple solutions in surrounding rock parameter inversion. The three-dimensional joint inversion algorithm of the dynamically coupled inversion module improves the accuracy of surrounding rock condition assessment, providing a reliable basis for risk warning and support decision-making. Furthermore, it achieves quantitative early warning of surrounding rock risks. The probabilistic early warning module reduces the probability of missed and false alarms by quantifying risk probabilities, improving construction safety. The adaptive support module can dynamically adjust support parameters to achieve a balance between support force and surrounding rock stress, balancing support effectiveness and engineering economy, and avoiding resource waste. The closed-loop system constructed by this solution enables dynamic iterative optimization throughout the entire construction process, adapting to complex geological conditions, broadening its applicability, reducing reliance on construction personnel experience, improving the intelligence and standardization of tunnel construction, promoting construction technology upgrades, and ensuring construction safety. Attached Figure Description

[0015] Figure 1 This is a system architecture diagram of the intelligent monitoring and support system for surrounding rock stability in tunnel construction according to the present invention.

[0016] Figure 2 This is a diagram showing the multi-source collaborative sensing module of the intelligent monitoring and support system for surrounding rock stability in tunnel construction, as described in this invention.

[0017] Figure 3 This is a data type diagram of the multi-source collaborative sensing module of the intelligent monitoring and support system for surrounding rock stability in tunnel construction, based on the present invention.

[0018] Figure 4 This is a flowchart illustrating the pre-construction preparation process for the intelligent monitoring and support method for surrounding rock stability in tunnel construction, based on the present invention.

[0019] Figure 5 This is the core flowchart of the construction process of the intelligent monitoring and support method for surrounding rock stability in tunnel construction according to the present invention.

[0020] Figure 6 This is a flowchart of the dynamic coupling inversion module to the adaptive support module of the intelligent monitoring and support method for surrounding rock stability in tunnel construction according to the present invention. Detailed Implementation

[0021] To facilitate understanding of this application, a more complete description will be provided below with reference to the accompanying drawings, which illustrate embodiments of the present application. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that the disclosure of this application will be thorough and complete.

[0022] Referring to the attached figures, an intelligent monitoring and support system and method for surrounding rock stability in tunnel construction is described. The intelligent monitoring and support system for surrounding rock stability in tunnel construction includes a multi-source collaborative sensing module, a dynamic coupling inversion module, a probabilistic early warning module, an adaptive support module, and a data transmission module. The multi-source collaborative sensing module integrates four monitoring technologies: distributed fiber optic sensing, acoustic emission monitoring, high-precision ground-penetrating radar, and drilling parameter acquisition. It uses a unified spatiotemporal reference calibration technique to solve the problem of inconsistent coordinate systems and sampling schemes of different sensors, and simultaneously collects surrounding rock strain, temperature, acoustic emission energy, wave velocity, resistivity, and drilling parameters. The data transmission module transmits the monitoring data collected by the multi-source collaborative sensing module to the dynamic coupling inversion module. The dynamic coupling inversion module performs three-dimensional joint inversion based on the monitoring data and updates the surrounding rock physical property field and seepage evolution model. The probabilistic early warning module generates risk levels and probabilities based on the inversion results and triggers early warning signals. The adaptive support module receives the early warning signals and adjusts the support parameters according to the real-time status of the surrounding rock, realizing closed-loop collaboration between monitoring and support.

[0023] As an improvement, the multi-source collaborative sensing module includes several distributed fiber optic sensors, acoustic emission sensors, ground-penetrating radar probes, and drilling parameter acquisition devices. All sensors and acquisition devices are calibrated with a unified spatiotemporal reference to ensure the spatiotemporal consistency of the acquired data and avoid the data silo effect.

[0024] As an improvement, the dynamic coupling inversion module adopts an original three-dimensional joint inversion algorithm of physical property parameters-seepage evolution-stress state, introduces strain rate and acoustic emission energy as dynamic constraints, constructs a dynamic evolution model of surrounding rock permeability, and explicitly describes the abrupt change behavior of seepage channels during the rapid connection of microfractures.

[0025] As an improvement, the probabilistic early warning module explicitly maps model uncertainty to a risk probability function. Combined with an anomaly detection model trained by machine learning algorithms, it constructs a multi-level risk probability early warning system, which can dynamically correct the risk probability based on the distribution of surrounding rock physical parameters and the degree of seepage evolution.

[0026] As an improvement, the adaptive support module includes an advanced small-diameter pipe grouting unit, a telescopic anchor bolt placement unit, a flexible shotcrete pouring unit, and an intelligent actuator. The intelligent actuator is used to control the three support units in a coordinated manner, so as to realize the real-time dynamic adjustment of support parameters.

[0027] A method for intelligent monitoring and support of surrounding rock stability for tunnel construction includes the following steps: Before construction, all sensors and acquisition devices in the multi-source collaborative sensing module are uniformly calibrated and deployed, a three-dimensional geological model of the tunnel is constructed, and historical engineering data is input to train the inversion algorithm of the dynamic coupling inversion module and the early warning algorithm of the probabilistic early warning module; During construction, multi-physical field data of the surrounding rock are synchronously collected through the multi-source collaborative sensing module and transmitted to the dynamic coupling inversion module through the data transmission module. The dynamic coupling inversion module performs three-dimensional joint inversion and updates the surrounding rock physical property parameter field and seepage evolution model in real time to ensure the synergy between monitoring data and the inversion process.

[0028] As an improvement, a risk warning step is also included: the probabilistic warning module receives the surrounding rock physical property parameter field and seepage evolution model data output by the dynamic coupling inversion module, identifies abnormal surrounding rock conditions through the anomaly detection model, maps the model uncertainty into risk probability, generates multiple risk levels and corresponding probabilities, and triggers warning signals of the corresponding level.

[0029] As an improvement, an adaptive support step is also included: the adaptive support module receives the early warning signal output by the probabilistic early warning module and the real-time status data of the surrounding rock, and controls the advanced small pipe grouting unit, the telescopic anchor bolt placement unit, and the flexible shotcrete pouring unit through the linkage of the intelligent actuator, adjusts the support parameters and executes the support operation.

[0030] As an improvement, in the adaptive support step, the support parameters are adjusted based on the deformation rate of the surrounding rock, the stress state, and the degree of seepage evolution to achieve a dynamic balance between the support force and the stress of the surrounding rock, thereby avoiding stress concentration damage caused by rigid support.

[0031] As an improvement, a dynamic iterative optimization step is also included: continuously collecting response data of the surrounding rock after support, feeding the response data back to the dynamic coupling inversion module and the adaptive support module, optimizing the inversion algorithm parameters and support strategy, and realizing dynamic iteration throughout the entire construction process.

[0032] The core objective of this invention is to solve the technical problems in existing tunnel construction, such as isolated surrounding rock monitoring data, strong multiple solutions in parameter inversion, and delayed support response. By constructing a closed-loop system of "multi-source collaborative perception - dynamic coupling inversion - probabilistic risk early warning - graded adaptive support", it achieves intelligent control of surrounding rock stability throughout the entire process, thereby improving the safety and economy of tunnel construction. The specific implementation method is as follows.

[0033] Specific implementation of intelligent monitoring and support system for surrounding rock stability in tunnel construction: In this embodiment, the intelligent monitoring and support system for surrounding rock stability in tunnel construction includes a multi-source collaborative sensing module, a dynamic coupling inversion module, a probabilistic early warning module, an adaptive support module, and a data transmission module. The modules work together to form a complete monitoring-support closed loop. The specific implementation details are as follows.

[0034] The multi-source collaborative sensing module is the core of the entire system's data acquisition, enabling comprehensive and seamless perception of the surrounding rock condition and avoiding data silos. This module specifically includes several distributed fiber optic sensors, acoustic emission sensors, ground-penetrating radar probes, and a drilling parameter acquisition device. All sensors and acquisition devices undergo unified spatiotemporal benchmark calibration before deployment to ensure spatiotemporal consistency of the acquired data. Specifically, the distributed fiber optic sensors are evenly spaced along the tunnel face and surrounding rock to collect rock strain and temperature data; acoustic emission sensors are deployed at key locations on the tunnel arch, arch waist, and sidewalls to capture acoustic emission energy signals generated by the propagation of micro-fractures in the surrounding rock; the ground-penetrating radar probe is installed on the tunnel boring machine, synchronously scanning the internal structure of the surrounding rock during the excavation process to collect wave velocity and resistivity data; the drilling parameter acquisition device is integrated at the end of the drill pipe to collect drilling parameters such as rotational speed and pressure in real time. The acquisition frequencies of all sensors and acquisition devices are kept synchronized. Through unified spatiotemporal benchmark calibration technology, the coordinate systems of different sensors are uniformly calibrated, resolving the problem of inconsistent sensor coordinate systems and sampling schemes, and ensuring effective fusion of various data types.

[0035] The data transmission module employs a combination of wired and wireless transmission methods. Wired transmission is used for data transmission from fixedly deployed sensors, while wireless transmission is used for data transmission from mobile devices such as drilling parameter acquisition devices, ensuring that monitoring data can be transmitted to the dynamic coupling inversion module in real time and stably. During data transmission, data encryption is used to prevent data loss or interference, ensuring data integrity and security.

[0036] The dynamically coupled inversion module is the core for accurately assessing the surrounding rock condition. It employs a unique three-dimensional joint inversion algorithm combining physical properties, seepage evolution, and stress state to address the problem of multiple solutions inherent in traditional single-physics-field inversion methods. To accurately characterize the abrupt change in seepage channels during the rapid connection of microfractures in the surrounding rock, a dynamic evolution model of surrounding rock permeability is constructed, introducing strain rate and acoustic emission energy as dynamic constraints to improve the accuracy and stability of the inversion results. The core formula of the dynamic evolution model of surrounding rock permeability is as follows: The symbols in the formula are explained below: Let be the permeability of the surrounding rock at time t, in meters. 2, is used to characterize the conductivity of the seepage channels inside the surrounding rock at time t, and is the core parameter for judging the degree of seepage evolution in the surrounding rock; The initial permeability of the surrounding rock, in meters. 2 Determined by geological survey data before construction, it serves as the benchmark value for permeability evolution calculation; The strain rate influence coefficient is a unitless coefficient determined by fitting historical engineering data based on the lithology of the surrounding rock of the tunnel. It is used to quantify the degree of influence of the surrounding rock strain rate on the evolution of permeability. Let t be the strain rate of the surrounding rock at time t, in seconds. -1 The data is collected by distributed fiber optic sensors in the multi-source collaborative sensing module. The acoustic emission energy influence coefficient is dimensionless and is determined based on the surrounding rock lithology fitting. It is used to quantify the influence of acoustic emission energy generated by the propagation of microfractures in the surrounding rock on permeability evolution. The acoustic emission energy of the surrounding rock at time t, expressed in J, is collected by an acoustic emission sensor. This formula directly correlates the surrounding rock strain rate, acoustic emission energy, and permeability, dynamically calculating the permeability of the surrounding rock at different times. It explicitly characterizes the abrupt change in seepage channels during the rapid connection of microfractures, providing accurate seepage evolution data support for subsequent risk warning and support decisions.

[0037] The probabilistic early warning module, based on the surrounding rock physical property parameter field and seepage evolution model data output by the dynamically coupled inversion module, achieves quantitative prediction of surrounding rock risk, avoiding missed and false alarms. This module explicitly maps model uncertainty to a risk probability function, and, combined with an anomaly detection model trained by machine learning algorithms, constructs a multi-level risk probability early warning system. The risk probability can be dynamically adjusted according to the distribution of the surrounding rock physical property parameter field and the degree of seepage evolution. The core formula for calculating the risk probability is as follows: The symbols in the formula are explained below: denoted as the probability of surrounding rock collapse at time t, which is dimensionless and ranges from [0,1]. It is used to quantitatively characterize the possibility of surrounding rock collapse at time t. The higher the probability value, the higher the risk. The permeability influence weighting coefficient is dimensionless and determined by fitting historical disaster data. It is used to quantify the influence weight of permeability evolution on collapse risk. and These are the permeability of the surrounding rock at time t and the initial time, respectively, with the same meaning as the formula above; This is a weighting coefficient for the influence of stress state, which is dimensionless and determined based on the mechanical properties of the surrounding rock. It is used to quantify the weighting of the influence of the stress state of the surrounding rock on the risk of collapse. The stress in the surrounding rock at time t, expressed in Pa, is obtained by the dynamic coupling inversion module. This formula integrates two core indicators—surround rock permeability evolution and stress state—to quantitatively calculate the risk probability. By setting different probability thresholds, it classifies risks into high, medium, and low levels, triggering corresponding early warning signals and providing a clear decision-making basis for adaptive support.

[0038] The adaptive support module includes an advanced small-diameter pipe grouting unit, a retractable anchor bolt placement unit, a flexible shotcrete pouring unit, and an intelligent actuator, used to achieve real-time matching between the support strategy and the surrounding rock condition. The intelligent actuator uses a PLC controller and establishes a communication connection with a probabilistic early warning module and a multi-source collaborative sensing module. It can receive early warning signals and real-time surrounding rock condition data in real time, and control the working parameters of the three support units in a coordinated manner to achieve real-time dynamic adjustment of the support parameters. Specifically, the advanced small-diameter pipe grouting unit is used for advanced reinforcement of the surrounding rock, the retractable anchor bolt placement unit is used to constrain surrounding rock deformation, and the flexible shotcrete pouring unit is used to form the support shell. The three work together to achieve a dynamic balance between the support force and the surrounding rock stress.

[0039] Specific implementation of intelligent monitoring and support methods for surrounding rock stability in tunnel construction: In this embodiment, the intelligent monitoring and support method for surrounding rock stability in tunnel construction is based on the aforementioned intelligent monitoring and support system for surrounding rock stability in tunnel construction. Specifically, it includes pre-construction preparation steps, construction process monitoring and inversion steps, risk warning steps, adaptive support steps, and dynamic iterative optimization steps. Each step is executed sequentially to form a closed-loop operation. The specific implementation process is as follows.

[0040] The first step is pre-construction preparation. Before the formal tunnel excavation, the unified calibration and deployment of all sensors and acquisition devices in the multi-source collaborative sensing module are completed. During the calibration process, a unified spatiotemporal reference is used to calibrate the sampling time and coordinate system of the distributed fiber optic sensors, acoustic emission sensors, ground-penetrating radar probes, and drilling parameter acquisition devices to ensure the spatiotemporal consistency of the data collected by various sensors. After deployment, a three-dimensional geological model of the tunnel is constructed. Basic parameters such as lithology, initial stress, and initial permeability of the tunnel surrounding rock are entered through geological exploration data. At the same time, monitoring data, inversion data, and disaster data from similar historical tunnel projects are input to train the three-dimensional joint inversion algorithm of the dynamic coupling inversion module and the anomaly detection model of the probabilistic early warning module. This ensures that the algorithm and model can adapt to the current geological conditions of the tunnel and improve the accuracy of subsequent inversion and early warning.

[0041] The second step is the construction process monitoring and inversion step. During tunnel excavation, the multi-source collaborative sensing module is activated to simultaneously collect multi-physics field data of the surrounding rock through various sensors and acquisition devices, including surrounding rock strain, temperature, acoustic emission energy, wave velocity, resistivity, and drilling parameters. The collected monitoring data is transmitted to the dynamic coupling inversion module via the data transmission module. The dynamic coupling inversion module calls the trained three-dimensional joint inversion algorithm, combined with the aforementioned dynamic evolution model of surrounding rock permeability. The system calculates the permeability of the surrounding rock at time t in real time, updates the surrounding rock physical property field and seepage evolution model, ensures the synergy between monitoring data and the inversion process, and realizes dynamic judgment of the surrounding rock condition.

[0042] The third step is the risk warning process. The probabilistic warning module receives the surrounding rock physical property parameter field and seepage evolution model data output from the dynamic coupling inversion module, calls the anomaly detection model to identify abnormalities in the surrounding rock condition, and simultaneously calculates the risk probability using the relevant formula. The probability of surrounding rock collapse at time t is calculated. Based on the preset risk threshold, a high-risk warning signal is triggered when the risk probability P(t) ≥ 0.8; a medium-risk warning signal is triggered when 0.5 ≤ P(t) < 0.8; and a low-risk warning signal is triggered when P(t) < 0.5. The warning signals are simultaneously transmitted to the adaptive support module and the construction control terminal to remind construction personnel to take corresponding prevention and control measures.

[0043] The fourth step is the adaptive support procedure. The adaptive support module receives early warning signals from the probabilistic early warning module and real-time rock condition data. Through intelligent actuators, it controls the advanced small-diameter pipe grouting unit, the retractable anchor bolt placement unit, and the flexible shotcrete pouring unit to adjust support parameters and execute support operations. The adjustment of support parameters is based on the deformation rate, stress state, and seepage evolution of the surrounding rock. Specifically, when a high-risk early warning signal is triggered, the intelligent actuator controls the advanced small-diameter pipe grouting unit to increase grouting pressure and grouting range, controls the retractable anchor bolt placement unit to densify anchor bolt spacing, and controls the flexible shotcrete pouring unit to increase shotcrete thickness, thereby enhancing support strength. When a medium-risk early warning signal is triggered, the basic support parameters remain unchanged, and the grouting pressure and anchor bolt spacing are appropriately adjusted to ensure a balance between support force and surrounding rock stress. When a low-risk early warning signal is triggered, conventional support parameters are used to avoid resource waste caused by over-support, achieving a dynamic balance between support force and surrounding rock stress, and preventing stress concentration failure caused by rigid support.

[0044] The fifth step is the dynamic iterative optimization step. After the adaptive support operation is completed, the multi-source collaborative sensing module continuously collects response data of the surrounding rock after support, including data on strain, stress, and permeability of the surrounding rock. This response data is fed back to the dynamic coupling inversion module and the adaptive support module. Based on the response data after support, the dynamic coupling inversion module optimizes the parameters of the three-dimensional joint inversion algorithm and adjusts the parameters in the two formulas mentioned above. , , , Equal coefficients are used to improve the accuracy of the inversion results; the adaptive support module optimizes the support strategy and support parameters based on the response data, and adjusts parameters such as grouting pressure, anchor spacing, and spraying thickness corresponding to different risk levels, so as to realize dynamic iterative optimization throughout the construction process, ensuring that the system and method can continuously adapt to changes in the surrounding rock condition and improve the support effect.

[0045] Through the above specific implementation methods, the intelligent monitoring and support system and method for surrounding rock stability in tunnel construction of the present invention can effectively solve many pain points of the existing technology, realize the precision of surrounding rock monitoring, the quantification of risk warning, and the self-adaptation of support operations, significantly improve the safety and economy of tunnel construction under complex geological conditions, and have broad engineering application value.

[0046] Beneficial Effects: This invention effectively solves the problem of isolated monitoring data in surrounding rock during tunnel construction, improving the completeness and synergy of monitoring data. The multi-source collaborative sensing module of this invention integrates four monitoring technologies: distributed fiber optic sensing, acoustic emission monitoring, high-precision ground-penetrating radar, and drilling parameter acquisition. Through unified spatiotemporal reference calibration technology, it addresses the issue of inconsistent coordinate systems and sampling schemes among different sensors, achieving synchronous acquisition and effective fusion of surrounding rock strain, temperature, acoustic emission energy, wave velocity, resistivity, and drilling parameters. This avoids the drawbacks of independent monitoring data and the inability to coordinate their application, providing comprehensive and accurate data support for subsequent surrounding rock condition inversion and risk early warning, breaking the limitations of traditional single-physical-field monitoring.

[0047] This invention addresses the challenge of multiple solutions in surrounding rock parameter inversion, improving the accuracy and stability of surrounding rock condition assessment. The dynamic coupling inversion module employs a unique three-dimensional joint inversion algorithm combining physical properties, seepage evolution, and stress state. It introduces strain rate and acoustic emission energy as dynamic constraints to construct a dynamic evolution model of surrounding rock permeability. This model explicitly characterizes the abrupt changes in seepage channels during the rapid connection of microfractures, abandoning the traditional experience-weighted data fusion approach. It improves the accuracy of inversion results from the source, effectively solving the technical pain points of traditional single-physical-field inversion, which suffers from high ambiguity and cannot accurately reflect the true state of the surrounding rock. This provides a reliable theoretical basis for risk warning and support decision-making.

[0048] This invention enables quantitative early warning of surrounding rock risks, reducing the probability of missed and false alarms in disaster reporting and improving construction safety. The probabilistic early warning module explicitly maps model uncertainties to a risk probability function. Combined with an anomaly detection model trained using machine learning algorithms, it constructs a multi-level risk probability early warning system. By quantitatively calculating the probability of surrounding rock collapse risk, it replaces the traditional qualitative level early warning mode. The risk probability can be dynamically corrected based on the distribution of surrounding rock physical parameters and the degree of seepage evolution, accurately identifying high-risk areas, shortening early warning response time, effectively avoiding missed and false alarms of geological disasters such as water inrush and collapse, reserving sufficient emergency response time for construction personnel, and significantly improving the safety of tunnel construction.

[0049] This invention achieves real-time matching between support strategies and surrounding rock conditions, improving support effectiveness and economy while avoiding resource waste. The adaptive support module of this invention uses intelligent actuators to control the advanced small-diameter pipe grouting unit, the retractable anchor bolt placement unit, and the flexible shotcrete pouring unit. Based on the risk level output by the probabilistic early warning module and the real-time state of the surrounding rock, it dynamically adjusts support parameters to achieve a dynamic balance between support force and surrounding rock stress. This avoids stress concentration failure caused by rigid support, improving the adaptability and durability of the support structure, while also avoiding resource waste caused by over-support. Simultaneously, it reduces construction hazards caused by improper support, balancing support effectiveness and engineering economy.

[0050] This invention constructs a closed-loop system of "monitoring-inversion-early warning-support" to achieve dynamic iterative optimization throughout the entire construction process, adapting to complex geological conditions. Through the collaborative work of each module, a complete closed-loop operation mechanism is formed. Through dynamic iterative optimization steps, it continuously collects response data of the surrounding rock after support, feeding back optimized inversion algorithm parameters and support strategies. This enables the intelligent monitoring and support system and method for surrounding rock stability in tunnel construction to continuously adapt to the dynamic changes in the surrounding rock condition, making it particularly suitable for tunnel construction under complex geological conditions such as deep-buried tunnels and karst water-rich strata, thus broadening the applicability of the technical solution.

[0051] This invention reduces reliance on construction workers' experience and enhances the intelligence level of tunnel construction. It replaces the traditional model of relying on construction workers' experience for monitoring data analysis, risk assessment, and support operations with an integrated design of intelligent monitoring, intelligent inversion, intelligent early warning, and adaptive support. This reduces human error, improves the intelligence and standardization of tunnel construction, reduces the labor intensity of construction workers, minimizes construction risks caused by insufficient experience, and promotes the upgrading and iteration of tunnel construction technology.

[0052] The present invention and its embodiments have been described above. This description is not restrictive, and the accompanying drawings are only one embodiment of the present invention; the actual structure is not limited thereto. In conclusion, if those skilled in the art are inspired by this description and design similar structures and embodiments without departing from the spirit of the invention, such designs should fall within the protection scope of the present invention.

Claims

1. An intelligent monitoring and support system for surrounding rock stability in tunnel construction, characterized by: The system includes a multi-source collaborative sensing module, a dynamic coupling inversion module, a probabilistic early warning module, an adaptive support module, and a data transmission module. The multi-source collaborative sensing module integrates four monitoring technologies: distributed fiber optic sensing, acoustic emission monitoring, high-precision ground-penetrating radar, and drilling parameter acquisition. It uses a unified spatiotemporal reference calibration technique to solve the problem of inconsistent coordinate systems and sampling schemes of different sensors, and synchronously collects surrounding rock strain, temperature, acoustic emission energy, wave velocity, resistivity, and drilling parameters. The data transmission module transmits the monitoring data collected by the multi-source collaborative sensing module to the dynamic coupling inversion module. The dynamic coupling inversion module performs three-dimensional joint inversion based on the monitoring data and updates the surrounding rock physical property field and seepage evolution model. The probabilistic early warning module generates risk levels and probabilities based on the inversion results and triggers early warning signals. The adaptive support module receives the early warning signals and adjusts the support parameters according to the real-time status of the surrounding rock, realizing closed-loop collaboration between monitoring and support.

2. The intelligent monitoring and support system for surrounding rock stability in tunnel construction according to claim 1, characterized in that: The multi-source collaborative sensing module includes several distributed fiber optic sensors, acoustic emission sensors, ground-penetrating radar probes, and drilling parameter acquisition devices. All sensors and acquisition devices are calibrated with a unified spatiotemporal reference to ensure the spatiotemporal consistency of the acquired data and avoid the data silo effect.

3. The intelligent monitoring and support system for surrounding rock stability in tunnel construction according to claim 1, characterized in that: The dynamic coupling inversion module adopts an original three-dimensional joint inversion algorithm of physical property parameters, seepage evolution, and stress state. It introduces strain rate and acoustic emission energy as dynamic constraints to construct a dynamic evolution model of surrounding rock permeability, and explicitly characterizes the abrupt change behavior of seepage channels during the rapid connection of microfractures.

4. The intelligent monitoring and support system for surrounding rock stability in tunnel construction according to claim 1, characterized in that: The probabilistic early warning module explicitly maps model uncertainty to a risk probability function. Combined with an anomaly detection model trained by machine learning algorithms, it constructs a multi-level risk probability early warning system, which can dynamically correct the risk probability based on the distribution of surrounding rock physical parameters and the degree of seepage evolution.

5. The intelligent monitoring and support system for surrounding rock stability in tunnel construction according to claim 1, characterized in that: The adaptive support module includes an advanced small-diameter pipe grouting unit, a retractable anchor bolt placement unit, a flexible shotcrete pouring unit, and an intelligent actuator. The intelligent actuator is used to control the three support units in a coordinated manner, enabling real-time dynamic adjustment of support parameters.

6. A method for intelligent monitoring and support of surrounding rock stability in tunnel construction, characterized by: This is achieved based on the intelligent monitoring and support system for surrounding rock stability in tunnel construction as described in any one of claims 1 to 5. The process includes the following steps: Before construction, all sensors and acquisition devices in the multi-source collaborative sensing module are uniformly calibrated and deployed, a three-dimensional geological model of the tunnel is constructed, and historical engineering data is input to train the inversion algorithm of the dynamic coupling inversion module and the early warning algorithm of the probabilistic early warning module; During construction, multi-physical field data of the surrounding rock are synchronously collected through the multi-source collaborative sensing module and transmitted to the dynamic coupling inversion module through the data transmission module. The dynamic coupling inversion module performs three-dimensional joint inversion and updates the surrounding rock physical property parameter field and seepage evolution model in real time to ensure the synergy between monitoring data and the inversion process.

7. The intelligent monitoring and support method for surrounding rock stability in tunnel construction according to claim 6, characterized in that: It also includes a risk warning step: the probabilistic warning module receives the surrounding rock physical property parameter field and seepage evolution model data output by the dynamic coupling inversion module, identifies abnormal surrounding rock conditions through the anomaly detection model, maps the model uncertainty into risk probability, generates multiple risk levels and corresponding probabilities, and triggers warning signals of the corresponding level.

8. The intelligent monitoring and support method for surrounding rock stability in tunnel construction according to claim 7, characterized in that: It also includes an adaptive support step: the adaptive support module receives the early warning signal output by the probabilistic early warning module and the real-time status data of the surrounding rock, and controls the advanced small pipe grouting unit, the telescopic anchor bolt placement unit, and the flexible shotcrete pouring unit through the linkage of the intelligent actuator, adjusts the support parameters and executes the support operation.

9. The intelligent monitoring and support method for surrounding rock stability in tunnel construction according to claim 8, characterized in that: In the adaptive support step, the support parameters are adjusted based on the deformation rate of the surrounding rock, the stress state, and the degree of seepage evolution to achieve a dynamic balance between the support force and the stress of the surrounding rock, thereby avoiding stress concentration damage caused by rigid support.

10. The intelligent monitoring and support method for surrounding rock stability in tunnel construction according to claim 6, characterized in that: It also includes a dynamic iterative optimization step: continuously collecting response data of the surrounding rock after support, feeding the response data back to the dynamic coupling inversion module and the adaptive support module, optimizing the inversion algorithm parameters and support strategy, and realizing dynamic iteration throughout the entire construction process.

Images