Rock-soil body multi-field coupling intelligent monitoring system

Abstract

The invention provides a rock-soil body multi-field coupling intelligent monitoring system comprising a multi-field sensing device configured to monitor parameters of a deformation field, a seepage field, a temperature field and a stress field of a rock-soil body; the edge calculation and transmission device is configured to perform preprocessing and real-time transmission on the multi-field sensing data; and the intelligent decision-making device is configured to analyze the preprocessed data based on a multi-field coupling model and generate disaster early warning information. According to the rock-soil body multi-field coupling monitoring system and method provided by the invention, synchronous monitoring of a deformation field, a seepage field, a temperature field and a stress field is realized through the multi-field sensing device; real-time data processing is performed in combination with an edge calculation and transmission device, and a dynamic early warning mechanism is established by using an intelligent decision-making device, so that the technical problems of multi-field data space-time correlation failure, insufficient multi-source data fusion precision and poor early warning mechanism adaptability are effectively solved, and the geological disaster early warning method has the remarkable advantages of improving the geological disaster early warning accuracy and timeliness.

Description

Technical Field

[0001] This invention relates to the field of geotechnical engineering monitoring technology, and in particular to a multi-field coupled intelligent monitoring system for soil and rock masses. Background Technology

[0002] As complex geological media, soil and rock masses are influenced by the coupling effects of multiple fields, including deformation, seepage, temperature, and stress. In scenarios such as mining, tunnel engineering, and slope protection, they are prone to geological disasters such as landslides, rock bursts, and water inrushes. Existing monitoring technologies face several technical bottlenecks: First, spatiotemporal correlation of multi-field data fails. Monitoring data from different physical field parameters exhibit significant differences in temporal resolution and spatial scale, making accurate spatiotemporal alignment difficult with traditional processing methods, leading to information gaps in the analysis of multi-field coupling mechanisms. Second, the accuracy of multi-source data fusion is insufficient. Different types of monitoring data have fundamental differences in physical meaning and dimensions, and existing fusion methods lack a correlation model based on physical constraints, resulting in large parameter inversion errors. Third, dynamic early warning mechanisms have poor adaptability; early warning thresholds are mostly based on fixed empirical values, lacking consideration for the dynamic evolution characteristics of soil and rock masses. Finally, cross-domain collaboration and standardization are lacking. Data from different monitoring institutions exhibit an "island effect," and multi-field coupled monitoring data lacks a unified standard. These problems severely restrict the accuracy and timeliness of early warning for geotechnical engineering disasters, and there is an urgent need to build a monitoring technology solution that integrates multi-field sensing, intelligent fusion, dynamic early warning, and cross-domain collaboration.

[0003] To address the aforementioned issues, existing technologies urgently need improvement. Summary of the Invention

[0004] In view of this, the present invention aims to provide a multi-field coupled intelligent monitoring system for soil and rock masses to solve or alleviate the technical problems existing in the prior art, and at least provide a beneficial option.

[0005] To address the aforementioned technical problems, this application provides a multi-field coupled intelligent monitoring system for soil and rock masses, comprising: a multi-field sensing device configured to monitor the deformation field, seepage field, temperature field, and stress field parameters of the soil and rock mass; an edge computing and transmission device configured to preprocess and transmit the multi-field sensing data in real time; and an intelligent decision-making device configured to analyze the preprocessed data based on a multi-field coupling model to generate disaster early warning information. The intelligent decision-making device is further configured to trigger an early warning and control the sensing device to adjust the monitoring frequency if abnormal multi-field parameters or equipment malfunctions are detected.

[0006] As a further preferred embodiment of this technical solution, the multi-field sensing device includes: a distributed optical fiber sensing component, which is spatially distributed along the rock and soil mass and configured to collect deformation and temperature field data; a multi-physics field sensor array, including an infrasound sensor, a seepage pressure sensor and a stress sensor, configured to simultaneously collect rock micro-fracture signals, pore water pressure and stress data; and a remote sensing monitoring component, configured to acquire surface deformation data.

[0007] As a further preferred embodiment of this technical solution: the distributed optical fiber sensing component includes: a fiber grating array, which is set in a key monitoring section inside the rock and soil mass and is configured to monitor strain distribution; a DAS distributed acoustic wave sensing unit, which is deployed along the borehole and is configured to capture rock vibration signals; and a temperature compensation subunit, which integrates a MEMS temperature sensor and is configured to correct optical fiber temperature drift error through a correction model.

[0008] The modified model is as follows:

[0009] Δε=K1ΔT+K2Δσ

[0010] In the formula:

[0011] Δε represents the strain change measured by fiber optic sensing.

[0012] ΔT represents the change in ambient temperature;

[0013] Δσ represents the change in stress on the soil and rock mass;

[0014] K1 is the temperature strain coefficient, used to quantify the weight of the influence of temperature change on the fiber optic strain measurement results.

[0015] K2 is the stress-strain coefficient, used to quantify the influence weight of stress changes on fiber optic strain measurement results.

[0016] As a further preferred embodiment of this technical solution, the edge computing and transmission device includes: an edge node processing unit configured to filter, reduce noise, and extract features from the raw sensor data; an IoT transmission unit configured to establish a low-latency data transmission link; and a local storage subunit configured to cache key data.

[0017] As a further preferred embodiment of this technical solution, the intelligent decision-making device includes: a multi-field coupling model library, storing thermal-fluid-solid coupling numerical models and parameter inversion algorithms; a machine learning inference unit, configured to predict the stability of soil and rock masses based on LSTM and random forest models; and a dynamic adjustment subunit for early warning thresholds, configured to update early warning criteria according to changes in geological conditions.

[0018] As a further preferred embodiment of this technical solution, the intelligent decision-making device further includes: a digital twin mapping unit, configured to construct a three-dimensional digital twin of the soil and rock mass to realize real-time mapping between monitoring data and the model; and a multi-source data fusion subunit, configured to fuse fiber optic, infrasound, and remote sensing data through a Bayesian network.

[0019] As a further preferred embodiment of this technical solution, it also includes: an adaptive control device, one end of which is connected to the intelligent decision-making device, and the other end of which is connected to the multi-field sensing device;

[0020] If the intelligent decision-making device determines that the data is abnormal, the adaptive control device adjusts the sampling frequency of the sensing device.

[0021] To address the aforementioned technical problems, another technical solution adopted in this application is: a multi-field coupled intelligent monitoring method for soil and rock masses, comprising the following steps: synchronously acquiring multi-field parameters of soil and rock mass deformation, seepage, temperature, and stress; performing edge preprocessing on the multi-field parameters to remove noise and extract characteristic parameters; inputting the preprocessed data into a multi-field coupled model to analyze the stability state of the soil and rock mass; if the monitored multi-field parameters exceed a preset threshold or the equipment malfunctions, triggering an early warning and adjusting the monitoring frequency.

[0022] As a further preferred embodiment of this technical solution, the simultaneous acquisition of multiple field parameters includes: acquiring deformation and temperature data through distributed optical fiber sensing components; capturing rock micro-fracture signals using infrasound sensors; and acquiring surface deformation data by combining InSAR technology.

[0023] As a further preferred embodiment of this technical solution, the edge preprocessing includes: removing noise from fiber optic sensing data using a wavelet threshold filtering algorithm; identifying abnormal vibration frequencies in infrasound signals using an adaptive feature extraction algorithm; and performing spatiotemporal alignment on multi-source data.

[0024] To solve the above-mentioned technical problems, another technical solution adopted in this application is: a computer device, the computer device including a processor and a memory coupled to the processor, the memory storing program instructions, when the program instructions are executed by the processor, causing the processor to perform the steps of the above-described intelligent monitoring method for multi-field coupling of soil and rock.

[0025] To solve the above-mentioned technical problems, another technical solution adopted in this application is: a storage medium storing program instructions capable of implementing the above-described intelligent monitoring method for multi-field coupling of soil and rock.

[0026] The embodiments of the present invention have the following advantages due to the adoption of the above technical solutions:

[0027] This application provides a multi-field coupled monitoring system and method for soil and rock masses. It realizes synchronous monitoring of deformation field, seepage field, temperature field and stress field through multi-field sensing device, performs real-time data processing by combining edge computing and transmission device, and establishes a dynamic early warning mechanism by using intelligent decision device. It effectively solves the technical problems of failure of spatiotemporal correlation of multi-field data, insufficient accuracy of multi-source data fusion and poor adaptability of early warning mechanism. It has significant advantages in improving the accuracy and timeliness of geological disaster early warning.

[0028] The above overview is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the invention will become readily apparent from the accompanying drawings and the following detailed description. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 This is a schematic diagram of the modules of the system of the present invention;

[0031] Figure 2 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0032] The embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0033] It should be understood that the following specific examples illustrate the implementation of this disclosure, and those skilled in the art can easily understand other advantages and effects of this disclosure from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. This disclosure can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this disclosure. It should be noted that, in the absence of conflict, the following embodiments and features in the embodiments can be combined with each other. Based on the embodiments in this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0034] It should be noted that various aspects of embodiments within the scope of the appended claims are described below. It will be apparent that the aspects described herein can be embodied in a wide variety of forms, and any particular structure and / or function described herein is merely illustrative. Based on this disclosure, those skilled in the art will understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects set forth herein can be used to implement the device and / or practice the method. Additionally, this device and / or method can be implemented using structures and / or functionalities other than one or more of the aspects set forth herein.

[0035] It should also be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this disclosure. The drawings only show the components related to this disclosure and are not drawn according to the number, shape and size of the components in actual implementation. In actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0036] Furthermore, specific details are provided in the following description to facilitate a thorough understanding of the examples. However, those skilled in the art will understand that the described aspects can be practiced without these specific details.

[0037] In the field of geotechnical engineering monitoring, existing technologies have long faced multi-dimensional technical bottlenecks. Traditional monitoring systems often employ single-physical-field data acquisition methods, such as monitoring only displacement or seepage parameters, resulting in incomplete capture of early warning information for disasters. Current data processing relies on centralized cloud computing, which cannot achieve real-time early warning. Furthermore, significant differences in data formats and acquisition frequencies among different monitoring devices cause difficulties in spatiotemporal alignment. In a case study of open-pit mine slope monitoring, the acquisition frequency of infrasound micro-fracture signals differed by three orders of magnitude from that of surface deformation data, leading to a slope slippage early warning delay of over 12 hours and preventing timely intervention.

[0038] To address the aforementioned issues, the inventors discovered that the spatiotemporal mismatch of multi-field parameters is the core contradiction restricting monitoring accuracy. Through analysis of the catastrophic evolution mechanism of soil and rock masses, they recognized the need to establish a multi-physics synchronous sensing system and designed an edge-end preprocessing module to eliminate data heterogeneity. Further research revealed that fixed early warning thresholds cannot adapt to the dynamic changes in soil and rock masses, necessitating the construction of a decision-making model with self-learning capabilities. Based on this, they proposed integrating a multi-dimensional sensor array at the sensing layer, deploying a real-time processing unit at the edge, and introducing a multi-field coupling analysis algorithm at the decision layer to form a closed-loop monitoring system.

[0039] Therefore, as Figure 1As shown, this application proposes a multi-field coupled monitoring system for soil and rock masses, comprising a multi-field sensing device, an edge computing and transmission device, and an intelligent decision-making device. The multi-field sensing device monitors the deformation field, seepage field, temperature field, and stress field parameters of the soil and rock masses; the edge computing and transmission device preprocesses and transmits the multi-field sensing data in real time; the intelligent decision-making device analyzes the preprocessed data based on the multi-field coupled model to generate disaster early warning information; when abnormalities in multi-field parameters or equipment failures are detected, an early warning is triggered and the sensing device is controlled to adjust the monitoring frequency.

[0040] The multi-field sensing device refers to a hardware combination integrating multiple sensing technologies, specifically employing distributed fiber optic sensors, infrasound sensors, seepage pressure sensors, and stress sensor arrays, used to simultaneously acquire multi-physics field parameters of the soil and rock mass's interior and surface. The edge computing and transmission device refers to computing equipment deployed at the monitoring site, specifically using embedded processors and 5G communication modules, used to perform noise reduction and filtering processing at the data source and establish a low-latency transmission channel. The intelligent decision-making device refers to a computing platform with data analysis capabilities, specifically using servers equipped with multi-field coupled numerical models and machine learning algorithms, used to assess the stability state of the soil and rock mass in real time and generate control commands.

[0041] Specifically, the multi-field sensing device captures the strain distribution within the soil and rock mass through a distributed optical fiber network, combines this with an infrasound sensor array to collect micro-fracture signals from the rock mass, and simultaneously acquires seepage and temperature field parameters. The edge computing and transmission device performs wavelet noise reduction on the raw data, extracts feature parameters, and uploads them to the intelligent decision-making device via a 5G network. The intelligent decision-making device inputs the pre-processed data into a thermal-fluid-solid coupling model, evaluates the stability of the soil and rock mass through a parameter inversion algorithm, and immediately triggers an early warning signal when abnormal parameters are detected, adjusting the sensor sampling frequency through a feedback control loop. For example, in a slope monitoring scenario, when the system detects a sudden change in seepage pressure and a surge in micro-fracture signals, it automatically increases the infrasound sensor sampling frequency from 1Hz to 100Hz, achieving precise capture of disaster precursors.

[0042] Compared to existing technologies, traditional systems rely on data from a single sensor and lack real-time processing capabilities. This solution addresses the challenge of spatiotemporal data alignment through multi-field synchronous sensing and edge computing. Existing technologies employ fixed threshold warning mechanisms; this solution utilizes dynamic coupling model analysis to achieve real-time optimization of warning criteria. Traditional methods require manual intervention in the event of equipment failure; this solution employs a closed-loop control mechanism to automatically adjust the monitoring strategy, ensuring system robustness.

[0043] Through the above technical solutions, this application achieves accurate spatiotemporal alignment of multi-physics field data, solving the problem of insufficient data fusion accuracy in traditional monitoring systems; by linking real-time processing and intelligent decision-making at the edge, the early warning response time is shortened to the minute level; by utilizing a dynamic parameter adjustment mechanism, the monitoring system can adapt to changes in complex geological conditions, significantly reducing the false alarm rate and the missed alarm rate.

[0044] This application further proposes a multi-field sensing device including a distributed optical fiber sensing component, spatially distributed along the rock and soil mass, configured to collect deformation and temperature field data; a multi-physics field sensor array, including an infrasound sensor, a permeability sensor, and a stress sensor, configured to simultaneously collect rock micro-fracture signals, pore water pressure, and stress data; and a remote sensing monitoring component, configured to acquire surface deformation data.

[0045] Among them, the distributed fiber optic sensing component refers to a fiber optic sensing system continuously deployed along the space of the rock and soil mass. Specifically, it can be implemented using a combination of fiber optic grating arrays and DAS distributed acoustic wave sensing units, inverting strain distribution by measuring the phase change of the optical signal. The multi-physics sensor array refers to a combined device integrating infrasound, seepage pressure, and stress sensors, specifically implemented using multi-channel synchronous acquisition circuits to capture the correlation characteristics between different physical quantities. The remote sensing monitoring component refers to deformation monitoring equipment based on satellite or airborne platforms, specifically implemented using InSAR interferometric radar technology, calculating surface displacement through microwave signal phase difference.

[0046] Specifically, distributed fiber optic sensing components are deployed along the monitoring sections inside the soil and rock mass, acquiring strain distribution data with centimeter-level spatial resolution using optical temporal reflectance technology, while simultaneously incorporating temperature compensation algorithms to eliminate environmental interference. The multiphysics sensor array employs an embedded synchronous triggering mechanism to ensure synchronized acquisition of infrasound signals, pore water pressure, and stress data on a microsecond-level timescale. Remote sensing monitoring components periodically acquire surface deformation data, which is then spatially registered with the fiber optic monitoring data through coordinate transformation, forming a cross-scale deformation field data fusion.

[0047] Compared with existing technologies, traditional monitoring systems often use a single type of sensor to operate independently, such as deploying only piezometers or displacement gauges, resulting in poor temporal synchronization of data from multiple fields and incomplete spatial coverage. This solution uses fiber optic sensing components to achieve continuous monitoring of the strain field inside the rock mass, combines this with infrasound sensors to capture micro-fracture events, and utilizes remote sensing technology to supplement information on large-scale surface deformation, thus constructing a multi-scale, multi-dimensional three-dimensional monitoring network.

[0048] Through the above technical solutions, this application effectively solves the problem of spatiotemporal correlation failure of multi-field data. By coordinating the work of fiber optic and infrasound sensors, it achieves the synchronous capture of micro-fracture events and macroscopic strain evolution within the rock mass. The synchronous acquisition mechanism of the multi-physics sensor array ensures the temporal consistency of seepage field and stress field parameters, providing an accurate data foundation for multi-field coupled analysis. The introduction of remote sensing monitoring components compensates for the spatial coverage deficiencies of traditional point monitoring, forming complementary verification between surface and subsurface data, and significantly improving the reliability of disaster precursor identification.

[0049] This application further proposes a distributed optical fiber sensing component, including a fiber optic grating array set in a key monitoring section inside the rock and soil mass to monitor strain distribution, a DAS distributed acoustic wave sensing unit deployed along the borehole to capture rock vibration signals, and a temperature compensation subunit integrating a MEMS temperature sensor to correct optical fiber temperature drift error through a correction model Δε=K1ΔT+K2Δσ.

[0050] The fiber grating array (FGA) refers to a sensor network formed by multiple fiber gratings connected in series. It can be fabricated using femtosecond laser writing technology and achieves strain monitoring by measuring the Bragg wavelength shift, used to acquire strain distribution data of key sections within the soil or rock mass. The DAS (Distributed Acoustic Sensing Unit) is an acoustic detection device based on phase-sensitive optical time-domain reflectometry (TDR) technology. It can use single-mode communication optical fiber as the sensing medium and captures rock mass vibration signals by analyzing the phase change of backscattered Rayleigh light. The temperature compensation subunit is an error correction module integrating a microelectromechanical system (MEMS) temperature sensor. It can use a multiphysics coupling model Δε = K1ΔT + K2Δσ for real-time compensation, where K1 and K2 are the temperature strain coefficient and stress strain coefficient obtained through laboratory calibration, respectively, used to eliminate the interference of ambient temperature changes on the fiber optic strain measurement results.

[0051] Specifically, fiber optic grating arrays are deployed at key monitoring sections within the soil and rock mass, such as the potential sliding surface of a landslide or the stress concentration zone at the tunnel arch. Strain distribution cloud maps are generated by measuring the wavelength offset of each grating node. DAS sensing units are deployed along the vertical borehole axis, utilizing the elastic waves generated by rock fracturing to induce fiber optic strain. Time-frequency analysis techniques are used to extract the frequency and energy characteristics of the vibration signal. The MEMS temperature sensor in the temperature compensation subunit collects real-time temperature data from the monitoring points. The temperature change ΔT and stress change Δσ are substituted into the compensation model to calculate the spurious strain component K1ΔT caused by temperature. This component is then subtracted from the total strain measurement Δε to obtain the true stress-strain component K2Δσ.

[0052] Compared with existing technologies, traditional distributed fiber optic monitoring systems typically use a single sensing fiber for strain measurement, failing to consider the impact of temperature drift on long-term monitoring data and lacking dedicated detection units for rock mass vibration signals. This solution achieves high spatial resolution strain field monitoring through a fiber optic grating array, combined with a DAS unit to capture the dynamic process of micro-fractures. Furthermore, it introduces a physical model-driven temperature compensation mechanism, solving the technical challenge of temperature and stress cross-interference in multi-field coupled monitoring.

[0053] Through the above technical solution, this application realizes high-precision synchronous monitoring of the strain field and vibration field inside the soil and rock mass, effectively eliminates measurement errors caused by temperature fluctuations, improves the accuracy of micro-fracture event identification, and provides reliable basic data support for multi-field coupling analysis.

[0054] This application further proposes an edge computing and transmission device in a multi-field coupled monitoring system for soil and rock masses, including an edge node processing unit configured to filter, denoise, and extract features from raw sensor data; a 5G / IoT transmission unit configured to establish a low-latency data transmission link; and a local storage subunit configured to cache key data.

[0055] The edge node processing unit refers to the computing module deployed at the monitoring site. Specifically, it can be implemented using an embedded processor combined with digital filtering algorithms. For example, wavelet threshold filtering can remove high-frequency noise, and sliding window mean filtering can eliminate baseline drift. Its function is to reduce the redundancy of the original data and extract effective features. The 5G / IoT transmission unit refers to the transmission module supporting multi-protocol communication. Specifically, it can be implemented using a hybrid networking approach of 5G modules and LoRa. For example, 5G can transmit high-frequency infrasound signals, and LoRa can transmit low-frequency temperature data. Its function is to dynamically allocate transmission resources according to data type to reduce overall latency. The local storage subunit refers to a storage device with power-loss protection. Specifically, it can be implemented using industrial-grade SSDs combined with a circular buffer management algorithm. For example, dual storage partitions can be set up to alternately overwrite and save critical data from the most recent 24 hours. Its function is to ensure data integrity during network interruptions.

[0056] Specifically, in geotechnical monitoring scenarios, strain data generated by distributed fiber optic sensing components is first processed in real-time by edge node processing units. For example, when the fiber Bragg grating array acquires the raw strain signal, the edge node processing unit separates noise components using wavelet transform algorithms and extracts strain abrupt change characteristic parameters. The preprocessed data is then transmitted to the cloud via a 5G / IoT transmission unit, with high-frequency vibration data preferentially transmitted via the 5G link, while low-frequency temperature data is transmitted via NB-IoT to reduce energy consumption. Simultaneously, the local storage subunit continuously records the processed characteristic parameters and raw waveform segments. When the network signal strength is detected to be below a threshold, it automatically switches to local storage mode until communication is restored, at which point the transmission resumes.

[0057] Compared to existing technologies, traditional monitoring systems typically upload raw data directly to cloud servers for processing, resulting in high bandwidth consumption and poor real-time performance. For example, in slope monitoring scenarios, traditional methods transmit approximately 2GB of raw infrasound data per hour, while this solution reduces the data volume to below 50MB by extracting effective features through edge nodes. Furthermore, existing technologies lack local caching mechanisms, making them prone to data loss during communication interruptions. This solution's local storage subunit, through dual-partition rotation storage, can completely preserve critical monitoring data during network outages.

[0058] Through the above technical solution, this application effectively solves the problem of high latency in massive monitoring data transmission, reducing data volume and improving transmission efficiency through edge preprocessing. Simultaneously, the local caching mechanism ensures data integrity under unstable network conditions, avoiding the data loss risk of traditional cloud-based direct transmission. In real-time slope monitoring scenarios, this technical solution can reduce data processing latency from minutes to seconds using traditional methods, significantly improving the timeliness of disaster early warning.

[0059] This application further proposes an intelligent decision-making device including a multi-field coupling model library, a machine learning inference unit, and a dynamic adjustment subunit for early warning thresholds. The multi-field coupling model library stores thermal-fluid-solid coupling numerical models and parameter inversion algorithms. The machine learning inference unit is configured to predict the stability of rock and soil based on LSTM and random forest models. The dynamic adjustment subunit for early warning thresholds is configured to update the early warning criteria according to changes in geological conditions.

[0060] The multi-field coupling model library refers to a database storing coupled numerical models of soil and rock thermodynamics, fluid mechanics, and solid mechanics. Specifically, it can be implemented using finite element or finite difference algorithms to construct three-dimensional numerical models, used to simulate the mechanical response of soil and rock under multiple field interactions. The machine learning inference unit refers to the algorithm module that performs time-series prediction and classification tasks. Specifically, it can use long short-term memory networks to process deformation time-series data, combined with random forest algorithms for stability classification, to capture the nonlinear characteristics of precursors to soil and rock instability. The dynamic adjustment subunit for early warning thresholds refers to a logic module with adaptive parameter update capabilities. Specifically, it can use sliding time windows to statistically analyze changes in geological parameters, combined with fuzzy control algorithms to update early warning criteria, to eliminate the risk of misjudgment caused by fixed threshold settings.

[0061] Specifically, the multi-field coupling model library uses a thermo-fluid-solid coupled numerical model to jointly solve preprocessed multi-field data, simulating the deformation response of soil and rock masses under the influence of temperature gradients, seepage pressure, and stress redistribution. The parameter inversion algorithm dynamically corrects the physical parameters of the soil and rock masses using a Bayesian optimization method based on the residuals between monitoring data and model output. In the machine learning inference unit, the LSTM model extracts features from strain time-series data acquired by fiber optic sensing, capturing nonlinear deformation patterns such as creep and relaxation; the random forest model performs multi-dimensional classification of infrasound signal spectral characteristics and seepage pressure mutation data to identify potential instability modes. The early warning threshold dynamic adjustment subunit receives real-time data on changes in rock mass structure surfaces detected by ground-penetrating radar. When the fracture propagation rate exceeds a set range, an automatic threshold update mechanism is triggered. By weighted fusion of historical disaster case data and real-time monitoring results, dynamic early warning criteria are generated.

[0062] Compared with existing technologies, traditional methods use fixed empirical thresholds for early warning judgments, failing to consider the dynamic characteristics of soil and rock parameters changing with geological conditions, and relying on a single numerical model for stability assessment. This proposed solution integrates multi-field coupled models with machine learning algorithms, achieving model complementarity in soil and rock stability analysis. Simultaneously, it dynamically adjusts early warning thresholds based on real-time geological data, effectively solving the misjudgment problems caused by model assumption biases and fixed thresholds in traditional methods.

[0063] Through the above technical solutions, this application solves the problems of poor adaptability of early warning mechanisms and weak model generalization ability in existing technologies, improves the accuracy of soil and rock parameter inversion, enhances the adaptability of multi-field coupled models to different geological conditions, and reduces the false alarm rate and missed alarm rate of disaster early warning. Specifically, it improves the accuracy of stress field simulation by correcting model input errors through dynamic parameter inversion; it identifies micro-fracture precursor signals that traditional methods failed to capture by using machine learning algorithms; and it avoids misjudgments caused by sensor drift or gradual changes in geological conditions through a dynamic adjustment mechanism for early warning thresholds.

[0064] This application further proposes that the intelligent decision-making device also includes a digital twin mapping unit and a multi-source data fusion subunit. The digital twin mapping unit is configured to construct a three-dimensional digital twin of the soil and rock mass to achieve real-time mapping between monitoring data and the model; the multi-source data fusion subunit is configured to fuse fiber optic, infrasound, and remote sensing data through a Bayesian network.

[0065] The digital twin mapping unit refers to a technical module that constructs a three-dimensional virtual model of soil and rock mass based on geological exploration data and real-time monitoring data. Specifically, it can be implemented using Building Information Modeling (BIM) and Geographic Information System (GIS) integration technologies. By mapping monitoring data at different spatiotemporal scales to a unified three-dimensional coordinate system, it solves the problem of spatial registration of multi-source data. The multi-source data fusion sub-unit refers to an intelligent processing module that integrates monitoring data of multiple physical quantities. Specifically, it can be implemented using an algorithm combining Bayesian networks and physical constraints. By establishing probabilistic dependencies between data from different sensors, it eliminates the impact of dimensional differences on fusion accuracy.

[0066] Specifically, during operation, the digital twin mapping unit first imports rock mass structure parameters obtained from geological exploration to establish an initial three-dimensional geological model. When the distributed fiber optic sensing component acquires strain distribution data, it maps the one-dimensional fiber optic strain data to the corresponding position in the three-dimensional model using a coordinate transformation algorithm, while simultaneously locating the micro-fracture signals detected by the infrasound sensor to the fracture surface inside the model. After data alignment, the multi-source data fusion subunit constructs a Bayesian network topology containing multiple parameters such as fiber optic strain, infrasound frequency, and surface deformation. Based on prior geological conditions, it calculates the conditional probability distribution of each parameter node and outputs a comprehensive stability assessment result through probabilistic inference. When the remote sensing monitoring component acquires new surface deformation data, the digital twin automatically updates the deformation field distribution and triggers the multi-field coupling model to recalculate the stress field distribution.

[0067] Compared to existing technologies, traditional methods, which use two-dimensional planar overlay to process multi-source data, struggle to accurately reflect the three-dimensional stress transmission path within soil and rock masses. Existing data fusion techniques often rely on manually set weighting coefficients, failing to dynamically adapt to parameter relationships under different geological conditions. This solution leverages the spatial mapping capabilities of a three-dimensional digital twin to achieve a unified representation of centimeter-level fiber optic data and hundred-meter-level remote sensing data. Simultaneously, it utilizes the probabilistic inference mechanism of Bayesian networks to automatically correct the confidence weights of data from different sensors.

[0068] Through the above technical solutions, this application effectively solves the problem of coupling analysis distortion caused by spatial registration errors of multi-source data, and improves the correlation accuracy between infrasound micro-fracture signals and fiber optic strain data. By dynamically updating the multi-field parameter distribution of the three-dimensional digital twin, the stress adjustment process inside the soil and rock mass can be reflected in real time, providing a visual analysis basis for disaster evolution trend prediction. Based on the multi-source fusion mechanism of Bayesian networks, the reliability of stability assessment results can still be maintained through probabilistic inference even when sensor data contains noise or is partially missing.

[0069] This application further proposes an adaptive control device, one end of which is connected to an intelligent decision-making device and the other end of which is connected to a multi-field sensing device; if the intelligent decision-making device determines that the data is abnormal, the adaptive control device adjusts the sampling frequency of the sensing device.

[0070] The adaptive control device refers to an actuator capable of dynamically adjusting the operating parameters of the sensing device according to decision commands. Specifically, it can be implemented using an embedded controller combined with a dynamic adjustment algorithm, used to quickly respond to and optimize monitoring resource allocation when data anomalies occur. Data anomaly detection refers to identifying deviations in monitoring parameters through preset threshold comparisons or machine learning models. Specifically, it can be implemented using LSTM-based time-series prediction residual analysis methods to accurately capture precursors of soil instability or equipment failure signals. Sampling frequency adjustment refers to dynamically changing the data acquisition rate according to the severity of the anomaly. Specifically, it can be implemented using a tiered control strategy, such as reducing the frequency to save energy during minor anomalies and increasing the frequency to enhance monitoring density during severe anomalies.

[0071] Specifically, when the intelligent decision-making device detects that the amplitude of the rock mass micro-fracture signal exceeds the safety threshold through multi-field coupling model analysis, it immediately sends a command to the adaptive control device. After parsing the command, the device generates a frequency adjustment signal through its built-in PID control algorithm, driving the infrasound sensor in the multi-field sensing device to increase the sampling rate from the conventional 1kHz to 10kHz. Simultaneously, for distributed fiber optic sensing components that are not malfunctioning, the adaptive control device appropriately reduces their sampling rate, thereby optimizing overall energy consumption while ensuring the accuracy of key data acquisition. In equipment failure scenarios, such as detecting signal drift from a pressure sensor, the adaptive control device will automatically switch to the backup sensor and synchronously adjust its sampling interval.

[0072] Compared to existing technologies, traditional monitoring systems often employ fixed sampling frequencies or manual adjustments, making it difficult to match the dynamic changes in soil and rock masses in real time. Existing technologies typically require manual configuration of sensor parameters, resulting in significant response delays and low adjustment accuracy. This solution, however, achieves automated dynamic optimization of the monitoring frequency through a closed-loop control architecture, effectively addressing the shortcomings of traditional methods in terms of timely response to abnormal events and rational resource allocation.

[0073] Through the above technical solution, this application can quickly adjust the operating status of the sensing device when abnormal data is detected, ensuring the collection density of key data while avoiding resource waste in non-abnormal areas. This dynamic adjustment mechanism significantly improves the monitoring system's ability to capture geological disaster processes and enhances the system's continuous operational stability under complex conditions, providing more reliable real-time data support for disaster early warning.

[0074] This application further proposes a multi-field coupled monitoring method for soil and rock masses, including: simultaneously acquiring multi-field parameters of soil and rock mass deformation, seepage, temperature and stress; performing edge preprocessing on the multi-field parameters to remove noise and extract characteristic parameters; inputting the preprocessed data into a multi-field coupled model to analyze the stability state of the soil and rock mass; and triggering an early warning and adjusting the monitoring frequency if the monitored multi-field parameters exceed the preset threshold or the equipment is abnormal.

[0075] The simultaneous acquisition of multiple field parameters refers to the simultaneous acquisition of different physical field data through multiple types of sensors. Specifically, this can be achieved by using distributed fiber optic sensing components and infrasound sensors in parallel acquisition, solving the data correlation failure problem caused by differences in temporal resolution in traditional methods. Edge preprocessing refers to localizing the raw data. This can be achieved by combining wavelet threshold filtering algorithms with adaptive feature extraction algorithms, reducing data transmission latency and improving data quality. Multi-field coupling model analysis refers to model calculations based on a combination of physical mechanisms and data-driven approaches. This can be achieved by using a thermo-fluid-structure interaction numerical model and LSTM neural network collaborative analysis, enhancing the accuracy of soil and rock stability assessment. Triggering early warning and adjusting monitoring frequency refers to establishing a dynamic response mechanism. This can be achieved by using Bayesian network anomaly detection and redundant sensor channel switching collaborative control, improving the system's adaptability to sudden operating conditions.

[0076] Specifically, in slope engineering monitoring scenarios, distributed fiber optic sensing components are used to collect real-time data on internal rock strain and temperature. Simultaneously, infrasound sensors capture micro-fracture signals, and satellite remote sensing is used to acquire surface deformation data, achieving simultaneous acquisition of data across scales from centimeters to hundreds of meters. Subsequently, wavelet thresholding denoising is applied to the fiber optic sensing data at edge nodes, spectral features are extracted from the infrasound signals, and a spatiotemporal registration algorithm is used to eliminate timestamp discrepancies between multi-source data. The preprocessed data is input into a thermo-fluid-structure interaction model for parameter inversion, and an LSTM model is used to predict deformation trends. When a sudden change in pore water pressure accompanied by abnormal vibration frequency is detected, an early warning signal is automatically triggered, and the sampling frequency of the infrasound sensor is increased to 100 times per second. At the same time, a backup pressure sensor is activated for data verification.

[0077] Compared to existing technologies, traditional methods rely on centralized cloud processing, resulting in response delays exceeding 10 minutes, and their fixed warning thresholds cannot adapt to dynamic conditions such as rainfall infiltration. This method, through real-time edge processing, controls data latency to within 1 second, and combines a Bayesian optimization algorithm to dynamically adjust the warning threshold, enabling the identification of landslide risks 15 minutes in advance, even under conditions of sudden rises in groundwater levels on slopes. Existing technologies typically have multi-source data fusion error rates exceeding 20%, while this method reduces the fusion error to below 5% through a physically constrained spatiotemporal alignment algorithm.

[0078] Through the above technical solutions, this application effectively solves the problem of early warning lag caused by spatiotemporal inaccuracies in multi-field data, improving the accuracy of correlation analysis between micro-fracture signals and seepage field changes by more than 40%. The dynamic threshold adjustment mechanism reduces the false alarm rate from 32% in traditional methods to 8%, while the monitoring interruption time caused by equipment failure is shortened to less than 30 seconds through redundant sensor channel switching. The synergistic application of multi-field coupling models and machine learning algorithms enables the area under the ROC curve for rock mass instability prediction to reach 0.93, significantly better than the baseline level of 0.75 for a single model.

[0079] This application further proposes to simultaneously acquire multiple field parameters, including obtaining deformation and temperature data through distributed fiber optic sensing components, capturing rock micro-fracture signals using infrasound sensors, and acquiring surface deformation data by combining InSAR technology.

[0080] Among them, the distributed fiber optic sensing component refers to a monitoring device composed of a fiber optic grating array and a DAS distributed acoustic wave sensing unit. Specifically, it can use a fiber optic grating array deployed along key monitoring sections inside the rock and soil mass to monitor strain distribution, combined with DAS units deployed inside the borehole to capture vibration signals, for the simultaneous acquisition of deformation and temperature field data inside the rock and soil mass. The infrasound sensor refers to a sensing device capable of detecting low-frequency acoustic wave signals. Specifically, it can use a piezoelectric ceramic sensor array deployed on the rock surface or inside the borehole to capture infrasound signals generated by micro-fractures in the rock mass, for the identification of damage evolution processes inside the rock mass. InSAR technology refers to synthetic aperture radar interferometry, specifically using radar equipment mounted on satellites or UAVs to acquire surface deformation interferograms, extracting millimeter-level deformation information through phase calculation, for monitoring large-scale surface displacement fields.

[0081] Specifically, during the monitoring of rock and soil masses, distributed fiber optic sensing components perceive the internal strain distribution of the rock and soil mass in real time through fiber optic grating arrays. Simultaneously, DAS units continuously collect vibration signals, and a temperature compensation model is used to correct the influence of ambient temperature on the measurement results, forming high-precision internal deformation and temperature field data. An infrasound sensor array collects low-frequency acoustic signals generated by micro-fractures in the rock mass at a preset sampling frequency, and identifies the location and intensity of fracture events through spectral analysis. InSAR technology periodically acquires radar image data, generates surface deformation interferograms, and performs spatial registration using a geographic information system to form surface displacement field data covering the entire monitoring area. These three types of data are synchronously collected using a unified time reference, forming a multi-scale monitoring dataset containing microscopic fracture signals, internal strain fields, and macroscopic surface displacement fields within the rock and soil mass.

[0082] In some specific implementations, distributed fiber optic sensing components can be deployed in monitoring boreholes inside the slope, while infrasound sensor arrays are arranged near the potential sliding surface. The InSAR data acquisition cycle can be dynamically adjusted according to external factors such as rainfall. When an anomaly in the infrasound signal is detected, the fiber optic sensing components can be triggered to increase the sampling frequency, while simultaneously adjusting the InSAR data acquisition interval, forming a collaborative response mechanism for multi-scale monitoring data.

[0083] Compared with existing technologies, traditional methods often employ a single monitoring method or collect data from different physical fields at different times, resulting in inconsistent spatiotemporal benchmarks. This solution integrates fiber optic sensing, infrasound monitoring, and InSAR technology to achieve simultaneous acquisition of microscopic fracture signals, strain fields, and macroscopic surface displacement fields within soil and rock masses. This solves the problem of time synchronization between microsecond-level dynamic signals and hourly-level remote sensing data in traditional methods, while also taking into account the spatial scale differences between centimeter-level local strain and hundred-meter-level regional deformation.

[0084] Through the above technical solutions, this application effectively solves the problem of spatiotemporal correlation failure of multi-field data, providing accurate raw datasets for subsequent spatiotemporal alignment and multi-source data fusion. Synchronous acquisition of infrasound signals and fiber optic strain data can accurately correlate internal rock mass fracture events with local strain responses, while spatiotemporal matching of InSAR data and internal monitoring results helps reveal the evolutionary relationship between surface deformation and deep rock mass damage, thus establishing a reliable data foundation for multi-field coupled analysis.

[0085] This application further proposes a method for multi-field coupled monitoring of soil and rock masses, which involves constructing a digital twin of the soil and rock mass to map the distribution of multi-field parameters in real time; dynamically updating the early warning threshold based on a historical disaster case database; and automatically switching to redundant sensing channels when a sensor failure is detected.

[0086] Among them, the digital twin of soil and rock refers to a virtual soil and rock model established through three-dimensional modeling technology. Specifically, it can be realized by BIM modeling or GIS spatial analysis technology. It is used to map deformation, seepage, temperature and stress parameters to the virtual model to solve the problem of spatial heterogeneity of multi-source data.

[0087] A historical disaster case database refers to a database that stores the correlation between historical monitoring data and disaster events. Specifically, it can be implemented using a relational database combined with time series analysis algorithms to extract anomaly pattern features under different geological conditions.

[0088] Redundant sensing channels refer to pre-deployed backup sensor groups, which can be implemented using multi-path signal acquisition circuits and fault detection algorithms. When the main sensor drifts or disconnects, it switches to the backup channel through preset logic to ensure the continuity of data acquisition.

[0089] Specifically, after deploying multi-physics sensors within the soil and rock mass, an initial digital twin is generated by fusing 3D laser scanning and ground-penetrating radar data. Real-time data collected by distributed fiber optic and infrasound sensors is mapped to the corresponding spatial coordinates of the twin, forming a dynamic distribution map of multi-field parameters. A historical disaster case database dynamically corrects the current warning threshold by associating stress-strain curves and seepage rate thresholds under similar geological conditions using a sliding time window algorithm. When a fiber optic sensing unit experiences fiber breakage or signal attenuation, a fault detection algorithm identifies the location of the abnormal node and controls a relay to switch to an adjacent redundant fiber optic channel to continue data acquisition.

[0090] Compared to existing technologies, traditional methods rely on fixed thresholds and lack data redundancy mechanisms, making them prone to monitoring interruptions when sensors fail. Furthermore, their early warning criteria cannot adapt to the nonlinear changes during the creep stage of soil and rock. This solution eliminates empirical bias through a dynamic threshold update mechanism, utilizes digital twins for multi-source data spatial registration, and maintains the robustness of the monitoring system through redundant channel switching.

[0091] Through the above technical solution, this application solves the problem of missing monitoring data caused by sensor failure, improves the analytical accuracy of the spatial distribution of multi-field parameters, enables the early warning threshold to be adaptively adjusted according to the actual mechanical state of the rock and soil, and effectively reduces the risk of misjudgment caused by equipment abnormality or changes in geological conditions.

[0092] For other details regarding the implementation techniques of each module in the above embodiments, please refer to the description of a multi-field coupled intelligent monitoring system for soil and rock in the above embodiments, which will not be repeated here.

[0093] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For system-type embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0094] An electronic device according to embodiments of the present disclosure includes a memory and a processor. The memory is used to store non-transitory computer-readable instructions. Specifically, the memory may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM) and / or cache memory. The non-volatile memory may, for example, include read-only memory (ROM), a hard disk, flash memory, etc.

[0095] The processor may be a central processing unit (CPU) or other processing unit with data processing and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions. In one embodiment of this disclosure, the processor is used to execute computer-readable instructions stored in the memory, causing the electronic device to perform all or part of the steps of the aforementioned embodiments of the present disclosure of a multi-field coupled intelligent monitoring system for soil and rock masses.

[0096] Those skilled in the art will understand that, in order to solve the technical problem of how to achieve a good user experience, this embodiment may also include well-known structures such as communication buses and interfaces, and these well-known structures should also be included within the protection scope of this disclosure.

[0097] like Figure 2 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. It illustrates a structural schematic diagram suitable for implementing the electronic device in the embodiment of the present disclosure. Figure 2 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0098] like Figure 2 As shown, an electronic device may include a processor (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on a program stored in read-only memory (ROM) or a program loaded from a storage device into random access memory (RAM). The RAM also stores various programs and data required for the operation of the electronic device. The processor, ROM, and RAM are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus.

[0099] Typically, the following devices can be connected to the I / O interface: input devices, such as sensors or visual information acquisition devices; output devices, such as displays; storage devices, such as magnetic tapes or hard drives; and communication devices. Communication devices allow electronic devices to communicate wirelessly or wiredly with other devices (such as edge computing devices) to exchange data. Although Figure 2 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have alternatively.

[0100] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device, or installed from a ROM. When the computer program is executed by a processor, all or part of the steps of a multi-field coupled intelligent monitoring system for soil and rock masses according to embodiments of this disclosure are performed.

[0101] For a detailed description of this embodiment, please refer to the corresponding descriptions in the foregoing embodiments, which will not be repeated here.

[0102] A computer-readable storage medium according to embodiments of the present disclosure stores non-transitory computer-readable instructions. When these non-transitory computer-readable instructions are executed by a processor, all or part of the steps of the aforementioned rock and soil multi-field coupled intelligent monitoring system according to various embodiments of the present disclosure are performed.

[0103] The aforementioned computer-readable storage media include, but are not limited to: optical storage media (e.g., CD-ROM and DVD), magneto-optical storage media (e.g., MO), magnetic storage media (e.g., magnetic tape or portable hard drive), media with built-in rewritable non-volatile memory (e.g., memory card), and media with built-in ROM (e.g., ROM cartridge).

[0104] For a detailed description of this embodiment, please refer to the corresponding descriptions in the foregoing embodiments, which will not be repeated here.

[0105] The basic principles of this disclosure have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details for implementation.

[0106] In this disclosure, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The block diagrams of devices, apparatuses, devices, and systems involved in this disclosure are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as "comprising," "including," "having," etc., are open-ended terms meaning "including but not limited to," and are used interchangeably with them. The terms "or" and "and" as used herein refer to the terms "and / or," and are used interchangeably with them unless the context clearly indicates otherwise. The term "such as" as used herein refers to the phrase "such as but not limited to," and is used interchangeably with it.

[0107] Additionally, as used herein, the “or” used in a list of items beginning with “at least one” indicates a separate list, such that a list of, for example, “at least one of A, B, or C” means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word “exemplary” does not imply that the described example is preferred or better than other examples.

[0108] It should also be noted that in the systems and methods of this disclosure, the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered as equivalent solutions to this disclosure.

[0109] Various changes, substitutions, and modifications can be made to the technology described herein without departing from the teachings defined by the appended claims. Furthermore, the scope of the claims of this disclosure is not limited to the specific aspects of the processes, machines, manufactures, events, means, methods, and actions described above. Currently existing or later-developed processes, machines, manufactures, events, means, methods, or actions that perform substantially the same function or achieve substantially the same result as the corresponding aspects described herein can be utilized. Therefore, the appended claims include such processes, machines, manufactures, events, means, methods, or actions within their scope.

[0110] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of this disclosure. Therefore, this disclosure is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0111] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this disclosure to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. A multi-field coupled intelligent monitoring system for soil and rock masses, characterized in that, include: The multi-field sensing device is configured to monitor the deformation field, seepage field, temperature field, and stress field parameters of the soil and rock mass; Edge computing and transmission devices are configured to preprocess and transmit multi-field sensing data in real time; The intelligent decision-making device is configured to analyze preprocessed data based on a multi-field coupling model and generate disaster early warning information; The intelligent decision-making device is also configured to trigger an early warning and control the sensing device to adjust the monitoring frequency if multiple abnormal parameters or equipment failures are detected.

2. The intelligent monitoring system for multi-field coupling of soil and rock masses according to claim 1, characterized in that: The multi-field sensing device includes: Distributed fiber optic sensing components are spatially distributed along the rock and soil mass and configured to collect deformation and temperature field data. A multiphysics sensor array, including an infrasound sensor, a pressure sensor, and a stress sensor, is configured to simultaneously acquire rock mass microfracture signals, pore water pressure, and stress data. The remote sensing monitoring component is configured to acquire surface deformation data.

3. The intelligent monitoring system for multi-field coupling of soil and rock masses according to claim 2, characterized in that: The distributed optical fiber sensing component includes: A fiber optic grating array is set up at a key monitoring section inside the rock and soil mass and is configured to monitor strain distribution. The DAS distributed acoustic wave sensing unit is deployed along the borehole and configured to capture rock vibration signals. The temperature compensation subunit, which integrates a MEMS temperature sensor, is configured to correct fiber temperature drift error through a correction model. The modified model is as follows: Δε=K1ΔT+K2Δσ In the formula: Δε represents the strain change measured by fiber optic sensing. ΔT represents the change in ambient temperature; Δσ represents the change in stress on the soil and rock mass; K1 is the temperature strain coefficient, used to quantify the weight of the influence of temperature change on the fiber optic strain measurement results. K2 is the stress-strain coefficient, used to quantify the influence weight of stress changes on fiber optic strain measurement results.

4. The intelligent monitoring system for multi-field coupling of soil and rock masses according to claim 1, characterized in that: The edge computing and transmission device includes: The edge node processing unit is configured to filter, reduce noise, and extract features from the raw sensor data; The Internet of Things (IoT) transmission unit is configured to establish a low-latency data transmission link; The local storage subunit is configured to cache critical data.

5. The intelligent monitoring system for multi-field coupling of soil and rock masses according to claim 1, characterized in that: The intelligent decision-making device includes: A multi-field coupling model library stores numerical models of thermal-fluid-structure interaction and parameter inversion algorithms; The machine learning inference unit is configured to predict the stability of soil and rock masses based on LSTM and random forest models. The early warning threshold dynamic adjustment sub-unit is configured to update the early warning criteria based on changes in geological conditions.

6. The intelligent monitoring system for multi-field coupling of soil and rock masses according to claim 5, characterized in that: The intelligent decision-making device also includes: The digital twin mapping unit is configured to construct a three-dimensional digital twin of the soil and rock mass, enabling real-time mapping between monitoring data and the model; The multi-source data fusion subunit is configured to fuse fiber optic, infrasound, and remote sensing data via a Bayesian network.

7. The intelligent monitoring system for multi-field coupling of soil and rock masses according to claim 1, characterized in that: Also includes: An adaptive control device is connected to an intelligent decision-making device at one end and to a multi-field sensing device at the other end. If the intelligent decision-making device determines that the data is abnormal, the adaptive control device adjusts the sampling frequency of the sensing device.

8. A multi-field coupled intelligent monitoring method for soil and rock masses, characterized in that, Includes the following steps: Simultaneously collect multi-field parameters of deformation, seepage, temperature, and stress of the soil and rock mass; Edge preprocessing is performed on multiple field parameters to remove noise and extract feature parameters; The preprocessed data is input into a multi-field coupled model to analyze the stability state of the soil and rock mass. If multiple parameters are detected to exceed preset thresholds or if equipment malfunctions, an alert will be triggered and the monitoring frequency will be adjusted.

9. The intelligent monitoring method for multi-field coupling of soil and rock masses according to claim 8, characterized in that, The synchronous acquisition of multiple field parameters includes: Deformation and temperature data are acquired through distributed fiber optic sensing components; Using infrasound sensors to capture signals of micro-fractures in rock masses; Obtaining surface deformation data using InSAR technology: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the multi-field coupled intelligent monitoring system for soil and rock as described in any one of claims 1-7.

10. The intelligent monitoring method for multi-field coupling of soil and rock masses according to claim 8, characterized in that, The edge preprocessing includes: Wavelet threshold filtering algorithm is used to remove noise from fiber optic sensing data; Abnormal vibration frequencies in infrasound signals are identified using an adaptive feature extraction algorithm. Spatiotemporal alignment of multi-source data.

Images