Blasting safety protection method based on unstable roadway tunneling

By using a variety of sensors and machine learning models in the mine for real-time monitoring and risk assessment, data transmission and processing problems in the tunnel monitoring system are solved, high-precision risk assessment and early warning are achieved, and excavation safety and efficiency are improved.

CN119026900AActive Publication Date: 2024-11-26SINOSTEEL MAANSHAN INST OF MINING RES CO LTD +1

Patent Information

Application Number
CN202410977408.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-22
Publication Date
2024-11-26
Estimated Expiration
2044-07-22

AI Technical Summary

Technical Problem

In mines, existing tunnel monitoring systems have problems such as instability in data transmission, limited processing capacity and imperfect risk assessment models, resulting in insufficient accuracy of risk warning and limited application range of high-cost sensors, making it difficult to realize multiple sensor data in multiple sensors fusion analysis.

Method used

Using multi-point strain gauge, fiber grating sensor and MEMS sensor for real-time monitoring, combined with LSTM network and random forest model, data preprocessing and risk assessment are carried out to achieve high-precision data acquisition and transmission, and automatically issue early warnings and take-outs according to risk levels. Physical protection measures.

Benefits of technology

It improves the safety and monitoring efficiency during tunnel excavation, ensures the accuracy and real-timeness of monitoring data, reduces safety hazards, and ensures the safety of operators and equipment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119026900A_ABST
    Figure CN119026900A_ABST
Patent Text Reader

Abstract

The invention discloses a blasting safety protection method based on unstable roadway tunneling, and belongs to the technical field of mine engineering and underground construction safety. The method comprises the following steps: S1, arranging a multi-point strain gauge, an MEMS sensor and an optical fiber grating sensor in a roadway, and acquiring a strain value, a stress value and Bragg wavelength change data in real time; s2, carrying out cleaning, denoising and normalization processing on the collected data; s3, predicting a future strain value, a stress value and Bragg wavelength change by using an LSTM (Long Short Term Memory) network; s4, classifying an LSTM prediction result and current monitoring data by using a random forest model, and evaluating a rock mass stability risk level; and S5, according to the risk level output by the random forest model, the system automatically gives an early warning and prompts to take corresponding physical protection measures. According to the invention, the safety and the monitoring efficiency in the roadway tunneling process are obviously improved, the potential safety hazard is reduced, and the safety of operators and equipment is guaranteed.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of mine engineering and underground construction safety, and more specifically to a blasting safety protection method based on unstable tunnel excavation. Background Art

[0002] In recent years, with the development of sensor technology, wireless transmission technology and data processing technology, tunnel monitoring solutions based on sensor networks have gradually been applied to mine safety monitoring. These systems use a variety of sensors (such as strain gauges, accelerometers, laser scanners, etc.) to collect data, realize real-time data transmission through wireless networks (such as ZigBee, LoRa and 5G), and centrally process and analyze data in data centers. Although these technologies have improved the monitoring accuracy and real-time performance to a certain extent, there are still some problems. First, the stability and reliability of data transmission is an important challenge. The mine environment is complex, and electromagnetic interference and signal shielding often lead to unstable wireless transmission signals, data loss and delays. Secondly, the existing data processing system has limited processing capacity. Faced with a large amount of real-time monitoring data, it is difficult to conduct effective analysis and processing in a timely manner, resulting in delayed risk assessment results. Finally, the existing risk assessment models are often not perfect and cannot fully consider various influencing factors, resulting in insufficient accuracy of risk warning. In addition, although some advanced monitoring technologies such as fiber grating sensors and MEMS sensors have been used in some mines, their application scope is still limited due to high costs, complex installation and maintenance, etc. At the same time, how to fuse and analyze the data from multiple sensors to form a comprehensive risk assessment result is also a problem that needs to be solved. Summary of the invention

[0003] The purpose of the present invention is to provide a blasting safety protection method based on unstable tunnel excavation. By installing multi-point strain gauges, fiber grating sensors and MEMS sensors to monitor the stress and displacement changes of the rock mass around the tunnel in real time, high-precision and high-frequency data acquisition and wireless transmission are achieved by using a data acquisition and transmission system, and comprehensive processing and risk assessment are performed in a data center to solve the problems raised in the above-mentioned background technology.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A blasting safety protection method based on unstable tunnel excavation includes the following steps:

[0006] S1: Multi-point strain gauges, MEMS sensors and fiber grating sensors are arranged in the tunnel to collect strain values, stress values ​​and Bragg wavelength change data in real time;

[0007] S2: Clean, denoise and normalize the collected data;

[0008] S3: Use LSTM network to predict future strain value, stress value and Bragg wavelength changes;

[0009] S4: Use the random forest model to classify the LSTM prediction results and current monitoring data to assess the rock mass stability risk level;

[0010] S5: Based on the risk level output by the random forest model, the system automatically issues an early warning and prompts the user to take appropriate physical protection measures.

[0011] Further, in step S1, a multi-point strain gauge is installed every 5 meters on the top plate of the tunnel, one at a depth of 0.5 meter and one at a depth of 1 meter. The strain gauge reflects the internal stress change by detecting the deformation of the rock mass; a MEMS sensor is installed every 3 meters on both sides of the tunnel, one at a depth of 0.5 meter and one at a depth of 1 meter. The MEMS sensor provides highly sensitive stress monitoring data by measuring the tiny stress changes inside the rock mass; a fiber grating sensor is installed every 10 meters on the bottom plate of the tunnel, one at a depth of 1 meter and one at a depth of 2 meters. The fiber grating sensor accurately measures the stress distribution of the bottom plate of the tunnel and deep inside by the change of the Bragg wavelength;

[0012] The strain value detected by the multi-point strain gauge is ΔL is the deformation length, L is the original length, and the strain value is converted into the stress value by Hooke's law: σ=E·∈, where: σ is the stress value, E is the elastic modulus of the material;

[0013] The stress value detected by the MEMS sensor is F is the applied force, A is the area under force;

[0014] The Bragg wavelength change detected by the fiber Bragg grating sensor is λ B is the initial Bragg wavelength, n eff is the effective refractive index of the optical fiber, ∈ is the strain value, P e is the photoelastic coefficient of the optical fiber;

[0015] Real-time evaluation and early warning system of LSTM and random forest, using LSTM network to predict future strain value, stress value and Bragg wavelength change, time series analysis:

[0016] LSTM unit formula: Forget gate: f t =σ(W f ·[h t-1 , x t ]+b f )

[0017] Among them, ft is the output of the forget gate, W f is the weight matrix of the forget gate, [h t-1 , x t ], is the concatenation of the hidden state of the previous moment and the current input, b f is the bias of the forget gate, σ is the sigmoid activation function;

[0018] Input Gate:

[0019] i t =o(W i .[h t-1 , x t ]+b i )

[0020]

[0021] Among them, i t is the output of the input gate, is the candidate cell state, W i and WC is the corresponding weight matrix, b i and b C is the bias value; σ is a symbol representing the sigmoid function, which is used to compress the input value to between 0 and 1; represents the candidate memory cell state at time step t, tanh is a symbol representing the hyperbolic tangent function, and the tanh function is used to compress the input value to between -1 and 1, W C is the weight matrix of the candidate memory cell state, h t-1 is the hidden state of the previous time step, x t is the input of the current time step, b c is the bias of the candidate memory cell state;

[0022] Cell status update:

[0023] Among them, C t is the cell state at the current moment, C t-1 is the cell state at the previous moment;

[0024] Output Gate:

[0025] o t =σ(W o ·[h t-1 , x t ]+b o )

[0026] h t =o t *tanh(C t )

[0027] Among them, t is the output of the output gate, h t is the hidden state at the current moment, W o is the weight matrix of the output gate, b o is bias;

[0028] The LSTM network is used to predict future strain values, stress values, and Bragg wavelength changes. The prediction formula is:

[0029] Among them, LSTM is the calculation process of the unit, which is used to predict the future strain value Stress value and Bragg wavelength variation and Respectively represent the predicted values ​​at time step t+1, ∈ t ,σ t and Δλ B,t They represent the input values ​​at time step t respectively. LSTM is a recurrent neural network used to process and predict time series data.

[0030] In step S4, the random forest classifier is a decision tree. Each decision tree is divided into rows according to the input features to generate categories represented by leaf nodes. Random forest: Among them, h(x) is the final prediction result of random forest, h i (x) is the prediction result of the i-th decision tree, and N is the number of decision trees;

[0031] Training phase: Use historically monitored strain values, stress values, Bragg wavelength change data and their corresponding risk levels to train the random forest model; input features include current and predicted strain values, stress values, and Bragg wavelength changes:

[0032]

[0033] Prediction stage: Input the current monitoring data and LSTM prediction data into the trained random forest model to predict the risk level:

[0034]

[0035] Further, in step S5, if When; among them, the current stress value σ current In the range of 0 to 5 MPa, and the stress change rate When the stress value is less than 0.1 MPa / h, the difference between the current stress value and the average stress value |σ current -σ mean |Less than the standard deviation σstd , and the risk coefficient R is less than 1, that is, it is judged as low risk, then continue routine monitoring and inspections, maintain existing protective measures, and generate a monitoring report once a week.

[0036] Furthermore, if σ std ≤σ current -σ mean <2σ std ; Among them, the current stress value σ current In the range of 5 to 7 MPa, and the stress change rate In the case of 0.1 to 0.5 MPa / h, the difference between the current stress value and the average stress value σ current -σ mean Greater than or equal to the standard deviation σ std If it is less than 2 times the standard deviation, it is judged as medium risk, and the monitoring frequency should be increased and support measures should be added.

[0037] Furthermore, if σ current >7MPa, |σ current -σ mean |≥2σ std ,R≥2; where, at the current stress value σ current Greater than 7MPa, and the stress change rate When the stress value is greater than 0.5 MPa / h, the difference between the current stress value and the average stress value |σ current -σ mean | Greater than or equal to 2 times the standard deviation σ std , and the risk coefficient R is greater than or equal to 2, which means it is judged as high risk, and the operation is stopped immediately, personnel are evacuated, emergency support and expert evaluation are implemented, a detailed reinforcement plan is formulated, and stress data is monitored in real time.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] The invention can monitor the stress and displacement changes of the rock mass around the tunnel in real time through multi-point strain gauges, fiber grating sensors and MEMS sensors. The collected stress data has high precision and reliability, ensuring the accuracy of the monitoring data; it has efficient data transmission and processing: the advanced wireless transmission technology is adopted to realize the efficient wireless transmission of the monitoring data. The data collector conditions, converts analog to digital and stores the sensor data, and transmits the data to the data center through the wireless transmission module. The data center pre-processes, stores and analyzes the received data, and generates a real-time risk assessment report by using machine learning models and statistical analysis methods; it has accurate risk assessment and early warning: through the calculation of the comprehensive risk index, the system can accurately assess the risk level of the tunnel. By setting a reasonable risk threshold, the system can timely warn different risk levels and guide on-site personnel to take corresponding protective measures. According to the risk assessment results, the system provides specific physical protection methods for three risk levels: low risk: continue routine monitoring and inspection, and maintain existing protective measures; medium risk: increase the monitoring frequency, increase support measures, such as spraying concrete and installing temporary brackets; high risk: emergency stop operation, evacuate personnel, implement emergency support and expert evaluation, and formulate detailed reinforcement plan. The present invention significantly improves the safety and monitoring efficiency during tunnel excavation, reduces potential safety hazards, and ensures the safety of operators and equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 The present invention is a flow chart of the method. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] See also Figure 1 The embodiment of the present invention provides a technical solution: a blasting safety protection method based on unstable tunnel excavation, comprising the following steps:

[0043] S1: Multi-point strain gauges, MEMS sensors and fiber grating sensors are arranged in the tunnel to collect strain values, stress values ​​and Bragg wavelength change data in real time;

[0044] A multi-point strain gauge is installed every 5 meters on the tunnel roof, with one at a depth of 0.5 meters and 1 meter. The strain gauge reflects the internal stress change by detecting the deformation of the rock mass, helping to monitor the stability of the tunnel roof, two sides and bottom plate in real time, and prevent rock mass instability and collapse; the strain gauge is installed at key positions of the tunnel roof, side and bottom plate, and the strain value of the rock mass is collected regularly; the strain gauge reflects the internal stress change by measuring the deformation of the rock mass, and regular strain data recording helps to monitor the sinking of the roof, the extrusion deformation of the two sides and the uplift of the bottom plate, etc. The strain value can be used to understand the response of the rock mass after being subjected to force and identify potential unstable areas;

[0045] A MEMS sensor is installed every 3 meters on both sides of the tunnel, with one at a depth of 0.5 meter and one at a depth of 1 meter. The MEMS sensor provides highly sensitive stress monitoring data by measuring the tiny stress changes inside the rock mass, helping to timely detect local instability and crack development on both sides of the tunnel; MEMS sensors are installed on the surface and inside the tunnel to monitor tiny stress changes and vibrations. These sensors have high sensitivity and high resolution and can capture subtle stress changes inside the tunnel; MEMS sensors have a high data acquisition frequency and can reflect the stress distribution and transmission inside the rock mass in real time, helping to identify local stress concentration and potential crack expansion risks;

[0046] A fiber grating sensor is installed every 10 meters on the tunnel floor, with one at a depth of 1 meter and 2 meters. The fiber grating sensor accurately measures the stress distribution on the tunnel floor and deep inside through the change of Bragg wavelength, providing high-precision stress data to ensure the long-term stability of the overall tunnel structure; the fiber grating sensor is installed on the tunnel floor and deep inside to measure the change of Bragg wavelength, and reflects the stress and deformation by detecting the change of Bragg wavelength; the fiber grating sensor has high precision and anti-interference ability, can work stably in harsh environments, and is particularly suitable for monitoring the stress changes in deep rock masses, providing long-term monitoring data on the stability of the overall structure;

[0047] The strain value detected by the multi-point strain gauge is ΔL is the deformation length, L is the original length, and the strain value is converted into the stress value through Hooke's law: σ=E·∈, where: σ is the stress value, E is the elastic modulus of the material; the stress value detected by the MEMS sensor is F is the force, A is the force area; the Bragg wavelength change detected by the fiber grating sensor is λ B is the initial Bragg wavelength, n eff is the effective refractive index of the optical fiber, ∈ is the strain value, P eis the photoelastic coefficient of the optical fiber. The data acquisition process not only includes the acquisition of real-time data, but also involves the preliminary processing and storage of data. The analog signal output by the sensor is filtered and amplified by the signal conditioning circuit to ensure the stability and accuracy of the signal. The conditioned signal is converted into a digital signal by the analog-to-digital converter (ADC) and then stored in the data collector. Each piece of data recorded by the data collector is accompanied by a timestamp and sensor location identifier for subsequent data analysis and processing. Real-time data is transmitted to the data center through a wireless transmission module (such as LoRa, 5G). The transmission process of sensor data needs to ensure the integrity and real-time nature of the data to avoid data loss and delay. After data transmission, the next step of data preprocessing is entered to provide basic data support for subsequent analysis and risk assessment.

[0048] S2: Clean, denoise and normalize the collected data; Data denoising: Use a low-pass filter to remove high-frequency noise; Data normalization: Standardize the data to a uniform scale for subsequent processing; Data preprocessing is to convert the collected raw data into high-quality data suitable for analysis. Raw data often contains noise, outliers and inconsistent formats, and a series of processing is required to ensure the accuracy and reliability of the data.

[0049] The first step is data cleaning to remove noise and outliers. Noise may come from environmental interference and equipment errors of sensors. Common methods include low-pass filtering and moving average filtering. Outlier detection and processing is to identify and correct sudden abnormal points in the data. These abnormal points may be caused by sensor failure or external interference. Next is data denoising. High-frequency noise in the data is removed by filtering algorithms. Common filtering algorithms include low-pass filtering and Gaussian filtering. They can smooth data curves, highlight trends and patterns in data, and reduce the impact of random fluctuations on analysis results. After data denoising, data normalization is performed. Data normalization is to convert data of different dimensions into the same scale range so that subsequent analysis models can treat each feature equally. Common normalization methods include minimum-maximum normalization and Z-score standardization. The pre-processed data needs to be time synchronized and formatted. Data from different sensors may have different sampling frequencies and timestamps. Time synchronization is to unify these data on the same time axis to ensure that each data point has a consistent time reference. Format unification is to convert data from different sources into a unified format to facilitate subsequent analysis and processing. The ultimate goal of data preprocessing is to improve the quality of data and provide a reliable data foundation for subsequent analysis and modeling. Through data cleaning, denoising, normalization, time synchronization and format unification, the accuracy and consistency of the data are guaranteed, so that the next step of LSTM prediction and random forest classification can be carried out on the basis of high-quality data.

[0050] S3: Use LSTM network to predict future strain value, stress value and Bragg wavelength changes:

[0051] 1. LSTM unit formula: Forget gate: f t =σ(W f ·[h t-1 ,x t ]+b f )

[0052] Input gate: i t =σ(W i ·[h t-1 ,x t ]+b i )

[0053] Cell status update:

[0054] Output gate: o t =σ(W o ·[h t-1 ,x t ]+b o ), h t =o t *tanh(C t )

[0055] 2. Prediction formula:

[0056] LSTM (Long Short-Term Memory Network) is a recurrent neural network (RNN) specifically designed for processing and predicting time series data. In mine tunnel monitoring, LSTM networks can effectively capture the temporal dynamics of strain values, stress values, and Bragg wavelength changes, and predict future stress and deformation trends. LSTM networks control the flow of information through a series of gating mechanisms (forget gate, input gate, and output gate), thereby remembering important information in long time series data and ignoring irrelevant information. Specifically, the forget gate determines which information in the current cell state needs to be discarded, the input gate determines which new information needs to be added to the cell state, and the output gate determines which parts of the current cell state will be passed as output to the next moment.

[0057] In implementation, the LSTM network needs to be trained first. By inputting a large amount of historical monitoring data (strain values, stress values, and Bragg wavelength changes), the LSTM network learns the time patterns and regularities of these data and adjusts internal parameters to minimize prediction errors. After training, the LSTM network uses the monitoring data at the current moment as input to predict the strain values, stress values, and Bragg wavelength changes at the next few moments. The output of the LSTM network is the predicted future strain values, stress values, and Bragg wavelength changes. These prediction results reflect the stress and deformation trends of the tunnel rock mass in the future. Through the prediction of the LSTM network, construction personnel can understand potential risks in advance and take preventive measures. The results of the LSTM network prediction will be used as input for the random forest model to perform risk assessment and classification. The application of the LSTM network not only improves the utilization rate of monitoring data, but also provides early warning of future stress and deformation, making the safety management of mine tunnels more proactive and efficient.

[0058] S4: Use the random forest model to classify the LSTM prediction results and current monitoring data to assess the rock mass stability risk level:

[0059] The random forest classifier is a decision tree. Each decision tree divides the rows according to the input features and generates the categories represented by the leaf nodes. Random forest: Among them, h(x) is the final prediction result of random forest, h i (x) is the prediction result of the i-th decision tree, and N is the number of decision trees;

[0060] Training phase: Use historically monitored strain values, stress values, Bragg wavelength change data and their corresponding risk levels to train the random forest model; input features include current and predicted strain values, stress values, and Bragg wavelength changes:

[0061]

[0062] Prediction stage: Input the current monitoring data and LSTM prediction data into the trained random forest model to predict the risk level:

[0063]

[0064] Random forest is an ensemble learning method based on decision trees, which is widely used for classification and regression tasks. In mine tunnel monitoring, random forest uses the future strain values, stress values ​​and Bragg wavelength changes predicted by the LSTM network, as well as the current monitoring data, to classify the stability and safety of the rock mass. Random forest improves the stability and accuracy of the model by constructing multiple decision trees. Each decision tree is trained by randomly extracting samples from the training data set, and the best split point is selected through a random subset of features to generate multiple different decision trees.

[0065] During classification, random forests vote on the prediction results of multiple decision trees and finally output the category. By integrating the prediction results of multiple models, random forests can effectively reduce the overfitting problem of a single decision tree and improve the generalization ability of the model. In practical applications, the random forest model is first trained using historical monitoring data (including strain values, stress values, Bragg wavelength changes and their corresponding risk levels). The feature vectors of the training data include the current and predicted strain values, stress values ​​and Bragg wavelength changes, and the target variable is the corresponding risk level (low risk, medium risk and high risk). After training, the random forest model uses the current monitoring data and LSTM prediction results as input for real-time risk classification. Specifically, the input feature vector includes the strain value, stress value and Bragg wavelength change at the current moment, as well as the future strain value, stress value and Bragg wavelength change predicted by the LSTM network. The random forest model passes these input features to each decision tree, which performs classification according to the splitting rules learned during the training process, and finally the random forest determines the risk level by majority voting.

[0066] S5: Based on the risk level output by the random forest model, the system automatically issues an early warning and prompts you to take appropriate physical protection measures:

[0067] Under low-risk conditions, the current stress value and stress change rate are both within a safe range, but monitoring and preventive measures are still required. The specific physical protection methods are as follows: Routine monitoring measures: Continue to use the existing sensor system for real-time monitoring, with the goal of ensuring that potential stress changes can be detected in a timely manner; Regular sensor calibration measures: Regularly calibrate multi-point strain gauges, fiber grating sensors, and MEMS sensors, with the goal of ensuring the accuracy of measurement data; Routine support measures: Maintain the existing anchor rods, anchor cables, and support systems, with the goal of providing basic structural stability; Regular inspection measures: Regularly check the integrity of the tunnel structure, including the roof, two sides, and bottom plate, with the goal of promptly detecting and repairing small-scale cracks and deformations; Monitoring report measures: Generate a monitoring report once a week, with the goal of recording and analyzing the current stress state and ensuring the long-term accumulation and analysis of monitoring data.

[0068] In medium-risk situations, the current stress value and stress change rate are close to but have not exceeded the safety threshold, and monitoring and support measures need to be strengthened. The specific physical protection methods are as follows: Measures to increase monitoring frequency: Increase the monitoring frequency from once an hour to once every 30 minutes, with the purpose of capturing stress changes more timely and preventing sudden risks; Measures to strengthen support: Increase the density of anchor rods and anchor cables, especially in stress concentration areas, with the purpose of enhancing the overall stability of the structure and preventing local instability; Measures to spray concrete: Spray a layer of concrete on the surface of the tunnel to increase the support strength, with the purpose of preventing rock spalling and small-scale collapse; Measures to install temporary supports: Install temporary steel supports in high-stress areas, with the purpose of providing additional support and reducing rock stress; Measures for detailed inspections: Conduct detailed inspections every day, focusing on stress concentration and deformation areas, with the purpose of promptly discovering and dealing with potential structural problems; Measures for detailed monitoring reports: Generate a detailed monitoring report every day, with the purpose of analyzing current stress changes and formulating further protective measures; Measures to prepare emergency plans: Formulate and prepare emergency plans, including evacuation routes and emergency support materials, with the purpose of ensuring rapid response when risks escalate.

[0069] In high-risk situations, the current stress value and stress change rate have exceeded the safety threshold, and emergency measures need to be taken to prevent accidents. The specific physical protection methods are as follows: Emergency stop operation measures: immediately stop all excavation and blasting operations, the purpose is to prevent further increase in rock stress and avoid collapse; evacuation measures: immediately evacuate all workers to ensure their safety, the purpose is to avoid casualties; implementation of emergency support measures: installation of steel arches and shotcrete, especially in high stress and deformation areas, the purpose is to quickly stabilize the rock mass and prevent large-scale collapse; organization of expert evaluation measures: organize geological and engineering experts to conduct on-site evaluation Assessment, purpose: to develop detailed reinforcement and repair plans; real-time monitoring measures: add real-time monitoring equipment to ensure that stress changes are kept track of at all times, purpose: to provide real-time data support and guide emergency and repair work; risk assessment report update measures: update the risk assessment report in real time based on the latest monitoring data, purpose: to provide the latest risk analysis and recommendations; construction prohibition measures: prohibit any construction activities before the high risk is lifted, purpose: to ensure the safety of personnel and equipment and avoid secondary risks; formulate detailed reinforcement plan measures: formulate and implement a detailed reinforcement plan based on the expert evaluation results, purpose: to stabilize the rock mass in the long term and restore the safety of the tunnel.

[0070] In summary, the present invention is a more efficient and reliable monitoring and protection technology, which improves the safety and efficiency of the tunnel excavation process. By integrating multiple sensor technologies, advanced data acquisition and transmission systems, and scientific risk assessment models, it can realize real-time monitoring and evaluation of the internal stress and displacement of the tunnel, so that effective protection measures can be taken in time to ensure construction safety. Through specific physical protection methods for different risk levels, it can ensure that various risks can be responded to in a timely and effective manner during the tunnel excavation process, ensuring the safety and efficiency of the operation.

[0071] The present invention and its embodiments are described schematically above, and the description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. Therefore, if a person skilled in the art is inspired by it and designs a structural method and an embodiment similar to the technical solution without creativity without departing from the purpose of the invention, they shall all fall within the protection scope of the present invention.

Claims

1. A blasting safety protection method based on unstable tunnel excavation, characterized by: The following steps are involved: S1: Multi-point strain gauges, MEMS sensors and fiber grating sensors are arranged in the tunnel to collect strain values, stress values ​​and Bragg wavelength change data in real time; S2: Clean, denoise and normalize the collected data; S3: Use LSTM network to predict future strain value, stress value and Bragg wavelength changes; S4: Use the random forest model to classify the LSTM prediction results and current monitoring data to assess the rock mass stability risk level; S5: Based on the risk level output by the random forest model, the system automatically issues an early warning and prompts the user to take appropriate physical protection measures.

2. A blasting safety protection method based on unstable tunnel excavation according to claim 1, characterized in that: In step S1, a multi-point strain gauge is installed every 5 meters on the top plate of the tunnel, one at a depth of 0.5 meters and one at a depth of 1 meter. The strain gauge reflects the internal stress change by detecting the deformation of the rock mass; a MEMS sensor is installed every 3 meters on both sides of the tunnel, one at a depth of 0.5 meters and one at a depth of 1 meter. The MEMS sensor provides highly sensitive stress monitoring data by measuring the tiny stress changes inside the rock mass; a fiber grating sensor is installed every 10 meters on the bottom plate of the tunnel, one at a depth of 1 meter and one at a depth of 2 meters. The fiber grating sensor accurately measures the stress distribution of the bottom plate of the tunnel and deep inside by the change of the Bragg wavelength; The strain value detected by the multi-point strain gauge is ∈, ΔL is the deformation length, L is the original length, and the strain value is converted into the stress value by Hooke's law: σ=E·∈, where: σ is the stress value, E is the elastic modulus of the material; The stress value detected by the MEMS sensor is σ, F is the applied force, A is the area under force; The Bragg wavelength change detected by the fiber Bragg grating sensor is Δλ B , λ B is the initial Bragg wavelength, n eff is the effective refractive index of the optical fiber, ∈ is the strain value, P e is the photoelastic coefficient of the optical fiber; The real-time evaluation and early warning system of LSTM and random forest uses LSTM network to predict future strain value, stress value and Bragg wavelength changes: LSTM unit formula: Forget gate: f t =σ(W f ·[h t-1 ,x t ]+b f ) Among them, f t is the output of the forget gate, W f is the weight matrix of the forget gate, [h t-1 ,x t ], is the concatenation of the hidden state of the previous moment and the current input, b f is the bias of the forget gate, σ is the sigmoid activation function; Input Gate: i t =σ(W i ·[h t-1 ,x t ]+b i ) Among them, i t is the output of the input gate, is the candidate cell state, W i and W C is the corresponding weight matrix, b i and b C is the bias value; σ is a symbol representing the sigmoid function, which is used to compress the input value to between 0 and 1; represents the candidate memory cell state at time step t, tanh is a symbol representing the hyperbolic tangent function, and the tanh function is used to compress the input value to between -1 and 1, W c is the weight matrix of the candidate memory cell state, h t-1 is the hidden state of the previous time step, x t is the input of the current time step, b c is the bias of the candidate memory cell state; Cell status update: Among them, C t is the cell state at the current moment, C t-1 is the cell state at the previous moment; Output Gate: the t =σ(W o ·[h t-1 ,x t ]+b o ) h t =o t *tanh(C t ) Among them, t is the output of the output gate, h t is the hidden state at the current moment, W o is the weight matrix of the output gate, b o is bias; The LSTM network is used to predict future strain values, stress values, and Bragg wavelength changes. The prediction formula is: Among them, LSTM is the calculation process of the unit, which is used to predict the future strain value Stress value and Bragg wavelength variation and Respectively represent the predicted values ​​at time step t+1, ∈ t ,σ t and Δλ B,t They represent the input values ​​at time step t respectively. LSTM is a recurrent neural network used to process and predict time series data. In step S4, the random forest classifier is a decision tree. Each decision tree is divided into rows according to the input features to generate categories represented by leaf nodes. Random forest: Among them, h(x) is the final prediction result of random forest, h i (x) is the prediction result of the i-th decision tree, and N is the number of decision trees; Training phase: Use historically monitored strain values, stress values, Bragg wavelength change data and their corresponding risk levels to train the random forest model; input features include current and predicted strain values, stress values, and Bragg wavelength changes: Prediction stage: Input the current monitoring data and LSTM prediction data into the trained random forest model to predict the risk level:

3. A blasting safety protection method based on unstable tunnel excavation according to claim 2, characterized in that: In step S5, if |σ current -σ mean |<σ std ,R<1; where the current stress value σ current In the range of 0 to 5 MPa, and the stress change rate When the stress value is less than 0.1 MPa / h, the difference between the current stress value and the average stress value |σ current -σ mean |Less than the standard deviation σ std , and the risk coefficient R is less than 1, that is, it is judged as low risk, then continue routine monitoring and inspections, maintain existing protective measures, and generate a monitoring report once a week.

4. The blasting safety protection method based on unstable tunnel excavation according to claim 2 is characterized in that: In step S5, if ,σ std ≤|σ current -σ mean |<2σ std ; Among them, the current stress value σ current In the range of 5 to 7 MPa, and the stress change rate In the case of 0.1 to 0.5 MPa / h, the difference between the current stress value and the average stress value |σ current -σ mean | Greater than or equal to the standard deviation σ std If it is less than 2 times the standard deviation, it is judged as medium risk, and the monitoring frequency should be increased and support measures should be added.

5. The blasting safety protection method based on unstable tunnel excavation according to claim 2 is characterized in that: In step S5, |σ current -σ mean |≥2σ std ,R≥2; where, at the current stress value σ current Greater than 7MPa, and the stress change rate When the stress value is greater than 0.5 MPa / h, the difference between the current stress value and the average stress value |σ current -σ mean | Greater than or equal to 2 times the standard deviation σ std , and the risk coefficient R is greater than or equal to 2, which means it is judged as high risk, and the operation is stopped immediately, personnel are evacuated, emergency support and expert evaluation are implemented, a detailed reinforcement plan is formulated, and stress data is monitored in real time.

Citation Information

Patent Citations

  • System for monitoring oil-gas pipeline in mining subsidence area

    CN102345797A

  • Dynamic monitoring system of ship lock back pull bar based on strain and monitoring method thereof

    CN106679582A

  • Power communication service reliability evaluation and prediction method and device based on LSTM and random forest hybrid model

    CN111260249A

  • Subway tunneling blasting vibration safety monitoring device based on multi-point distribution

    CN117454114A

  • Bridge structure health monitoring system based on Internet of Things

    CN209148032U

Cited By

  • Building electrical safety risk intelligent diagnosis method and system based on big data

    CN120046007A

  • Blasting vibration monitoring and influence range prediction method for long and large tunnel in environment sensitive area

    CN120372386A

  • Real-time wireless monitoring system and method for supporting effect of high-strength light-weight steel arch roadway

    CN120782423A

  • High-strength lightweight steel arch roadway support effect real-time wireless monitoring system and method

    CN120782423B

  • Deep ore rock stability rapid assessment method and system based on RMR classification

    CN121256631A