Real-time surrounding rock stability monitoring system and method based on distributed intelligent anchor rods

Abstract

The invention belongs to the field of anchor rod stress monitoring, and discloses a surrounding rock stability real-time monitoring system and method based on distributed intelligent anchor rods. A power supply module; an analysis processing terminal; a model optimization module; a display module; the monitoring method comprises the steps that S1, the anchor rod body is installed, and data are collected; the method comprises the following steps: S1, acquiring data, S2, completing data transmission, S3, processing and analyzing the data to obtain a stability evaluation result, S4, giving an alarm according to the evaluation result, and S5, predicting the future stability of the surrounding rock and giving an alarm according to a prediction result. According to the technical scheme, each anchor rod body is an independent measuring point, the use efficiency is improved, wireless networking expansion can be achieved through the wireless communication module, all the anchor rod bodies are included in the monitoring range, all-weather, unattended and real-time automatic uploading of stress / strain information of each rod point is achieved, and the overall and local conditions of surrounding rock supporting can be comprehensively reflected.

Description

Technical Field

[0001] This invention relates to the field of anchor bolt stress monitoring, and in particular to a real-time monitoring system and method for surrounding rock stability based on distributed intelligent anchor bolts. Background Technology

[0002] In fields such as mining and tunnel engineering, the stability of the surrounding rock is directly related to the safety of construction and the service life of the project. As a key component of the support system, the stress state and bearing capacity of the anchor bolt are important indicators reflecting the stability of the surrounding rock.

[0003] Traditional anchor bolt monitoring systems have several limitations: Firstly, traditional stress / strain sensor systems are mostly general-purpose designs, making them difficult to integrate and be compatible with existing anchor bolt technologies and applications. This results in the sensor system and anchor bolt design being independent of each other, increasing the overall size and weight, raising application costs, and making it difficult to adapt to complex engineering environments. Secondly, most existing anchor bolt monitoring systems use manual intermittent sampling or fixed-point monitoring of a few anchor bolts, uploading the sampled data to the host computer for analysis. This method cannot achieve large-scale real-time monitoring of the actual support status of thousands of anchor bolts, and cannot accurately and in real-time reflect the support status of the entire roadway and surrounding rock in both space and time, posing safety hazards and poor reliability issues. Summary of the Invention

[0004] The present invention aims to provide a real-time monitoring system and method for surrounding rock stability based on distributed intelligent anchor bolts, so as to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: A real-time monitoring system for surrounding rock stability based on distributed smart anchors, comprising: Data acquisition module; the acquisition module includes an anchor bolt body, the anchor bolt body is connected to a wireless stress / strain micro-sensor, a signal processing unit and a wireless communication unit, the signal processing unit is electrically connected to the wireless stress / strain micro-sensor, and the wireless communication unit is electrically connected to the signal processing unit; Power supply module; the power supply module provides power to the wireless stress / strain microsensor, signal processing unit and wireless communication unit; Display module; the display module is used to display the processing results; Analysis and processing terminal; the analysis and processing terminal includes a data receiving module, a data processing and analysis module, a prediction module, a storage module, and an early warning module; The wireless communication unit is electrically connected to the data receiving module. The data receiving module is used to receive data collected by the data acquisition module. The data processing and analysis module is used to process and analyze the received data and complete the assessment of the surrounding rock stability according to the preset assessment model. The prediction module is connected to the data processing and analysis module. The prediction module predicts the future stability trend of the surrounding rock based on the prediction model built based on historical and real-time data. Model optimization module; the model construction and optimization module is used to optimize and evaluate the model.

[0006] Preferably, the wireless stress / strain microsensor is fabricated using carbon fiber and silicone elastomer as the main raw materials combined with micron-level processing technology.

[0007] Preferably, the wireless communication unit adopts low-power wide-area network communication technology, which enables multiple data acquisition modules to be infinitely networked and expanded.

[0008] Preferably, the data processing and analysis module includes a data preprocessing unit, a feature extraction unit, and a stability evaluation unit; the data preprocessing unit is used to filter, denoise, and process outliers in the received data; the feature extraction unit is used to extract feature parameters related to the stability of the surrounding rock from the preprocessed data; the stability evaluation unit includes an evaluation model, and the stability evaluation unit is used to evaluate the stability of the surrounding rock based on the feature parameters and the preset evaluation model.

[0009] A method for real-time monitoring of surrounding rock stability based on distributed smart anchors includes the following steps: S1. Install the anchor body in the surrounding rock. Install multiple sets of anchor bodies according to the area of ​​the surrounding rock. Number the wireless stress / strain micro-sensors on each set of anchor bodies. Collect the stress / strain data of the corresponding anchor body in real time through the wireless stress / strain micro-sensors. S2. The signal processing unit processes and converts the acquired stress / strain data to obtain a digital signal, which is then transmitted to the data receiving module via the wireless communication unit; the data receiving module then sends the digital signal to the data processing and analysis module. S3. The data preprocessing unit of the data processing and analysis module preprocesses the digital signal. The preprocessing includes filtering, noise reduction and outlier removal of the data. The feature extraction unit extracts features from the preprocessed data to obtain feature parameters. The feature parameters are input into a preset evaluation model for stability evaluation. The stability evaluation results are then sent to the display module for display. At the same time, the data is stored through the storage module. S4. Further analyze the data through the prediction module to generate a prediction of the stress / strain change trend for a future preset time period; input the predicted trend data into the data processing and analysis module, and obtain the prediction results of the surrounding rock stability within the expected time period according to step S3. S5. When the data processing and analysis module determines that the surrounding rock has an abnormal stability, it issues an early warning signal through the early warning module. When it predicts that a danger will occur, it outputs the expected time period of the danger and displays the number and location of the wireless stress / strain micro-sensor that has detected the abnormality in the display module, so as to facilitate the staff to conduct fixed-point inspections.

[0010] Preferably, in step S3, the mean method is used to filter the data and remove high-frequency noise, and the 3σ criterion is used to identify and remove outliers in the data.

[0011] Preferably, the characteristic parameters in step S3 include the maximum stress / strain value, minimum stress / strain value, average stress / strain value, rate of change, and cumulative change.

[0012] The beneficial effects of this technical solution compared to existing technologies are as follows: (1) This technical solution is equipped with a data acquisition module. The wireless stress / strain micro-sensor is made of carbon fiber and silicone elastomer as the main materials and is manufactured by micron-level processing technology. The product is small in size and light in weight. The wireless stress / strain micro-sensor, signal processing unit and wireless communication unit are integrated into the anchor rod, which overcomes the problems of separation between the traditional sensing system and the anchor rod, poor compatibility and adaptability, and improves the efficiency of use. The distributed intelligent anchor rod is used to complete multi-point accurate measurement. Each anchor rod body is an independent measurement point. It can be infinitely networked and expanded through the wireless communication module to include all anchor rod bodies in the monitoring range, realize all-weather, unattended, real-time automatic uploading of stress / strain information of each rod point, overcome the limitations of existing anchor rod monitoring systems such as small sampling data, inaccurate spatial and temporal distribution, cumbersome process and high cost, and can comprehensively reflect the overall and local conditions of the surrounding rock support.

[0013] (2) This technical solution analyzes and processes the data through the analysis and processing terminal, filters, reduces noise and handles outliers, improves the accuracy of data processing, and thus improves the accuracy of subsequent assessment of surrounding rock stability; the prediction module can predict the future trend of surrounding rock stability based on historical and real-time data, realizing the role of early warning. Workers can take corresponding protective measures in advance according to the predicted structure, greatly reducing the risk of sudden accidents and improving construction safety.

[0014] (3) The wireless stress / strain microsensor of this technical solution has a low manufacturing cost, and the distributed networking design avoids the cost of large-scale wiring, reduces the cost of use and manual maintenance, and has strong stability and high accuracy, making it easy to promote and use on a large scale.

[0015] (4) Traditional sensors are mostly independent metal-encapsulated structures, which are large in size (usually more than 50 mm in diameter and more than 100 mm in length), requiring additional installation space. They cannot be deeply integrated with the anchor bolt body and tend to protrude from the support surface, making them inconvenient to use. In contrast, the wireless stress / strain micro-sensor in this technical solution is made of carbon fiber and silicone elastomer as the main raw materials, combined with micron-level processing technology. Its volume is only 1 / 5 to 1 / 10 of that of traditional sensors. It can be directly integrated into the inside or surface of the anchor bolt body without changing the original structure and size of the anchor bolt, greatly enhancing its performance. Secondly, traditional sensors require drilling holes and fixing them separately near the surrounding rock or anchor bolt. Some devices also require laying special cables, making the installation process cumbersome and in narrow spaces. In scenarios such as tunnels and high-risk mining areas, the operation is extremely difficult. In this technical solution, the wireless stress / strain micro-sensors are installed synchronously with the anchor bolt body, eliminating the need for additional drilling, fixing brackets, or complex wiring. A single person can complete the sensor assembly and deployment for a single anchor bolt, greatly improving installation efficiency. Finally, traditional sensors often rely on manual intermittent sampling or only monitor a few key anchor bolts at fixed points. The sampling frequency is low, and the limited wiring range makes it impossible to cover all anchor bolts, easily missing local risk points. In this technical solution, each wireless stress / strain micro-sensor is independently numbered, enabling accurate collection of stress / strain data for a single anchor bolt. Combined with wireless networking, it achieves "measurement for every bolt," eliminating data blind spots and greatly improving monitoring accuracy. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the monitoring system provided by the present invention; Figure 2 A flowchart illustrating the monitoring method provided by this invention; Detailed Implementation The present invention will now be described in further detail with reference to the accompanying drawings and embodiments: A real-time monitoring system for surrounding rock stability based on distributed smart anchors, comprising: The data acquisition module includes an anchor bolt body, which is connected to a wireless stress / strain microsensor, a signal processing unit, and a wireless communication unit. The signal processing unit is electrically connected to the wireless stress / strain microsensor, and the wireless communication unit is electrically connected to the signal processing unit. The wireless stress / strain microsensor, signal processing unit, and wireless communication unit are integrated on a single anchor bolt. The wireless stress / strain microsensor is fabricated using carbon fiber and silicone elastomer as the main raw materials combined with micron-level processing technology. The wireless communication unit adopts low-power wide-area network communication technology, such as LoRa technology, enabling multiple data acquisition modules to be infinitely networked and expanded.

[0017] The wireless stress / strain microsensor is prepared using carbon fiber and silicone elastomer as the main composite raw materials, supplemented with conductive functional additives, and encapsulated with epoxy resin as a protective material. The first step in fabricating a wireless stress / strain microsensor is to mix carbon fiber, silicone elastomer matrix, and conductive functional additives in a planetary ball mill until homogeneous. In this embodiment, nano-silver powder (particle size 20μm-50μm) is selected as the conductive functional additive to form a conductive composite slurry. The second step involves using micro-injection molding to inject the conductive composite slurry into a micrometer-scale mold. After cooling and solidification, a sensing core is formed, which is then removed. The third step involves using magnetron sputtering to deposit 80-nanometer-thick copper electrodes at both ends of the sensing core, with micro-pads pre-installed at the copper electrode leads. The fourth step involves using wire bonding to connect the electrode pads to the pins of a micro-signal conditioning chip to form the sensor. The fifth step involves placing the sensor in a polyimide encapsulation mold, filling it with epoxy resin, removing air bubbles through vacuum, and curing to complete the encapsulation.

[0018] Before preparing the anchor body, the anchor body is embedded in a groove in the middle. When installing the wireless stress / strain micro-sensor, the first step is to put the sensor into the groove and fill the gap between the groove and the sensor with thermally conductive silicone. The second step is to cover the groove with a metal cover plate of the same material as the anchor body and seal it by laser welding to complete the installation of the sensor and the anchor body.

[0019] During operation, the built-in miniature signal conditioning chip of the sensor amplifies and filters the resistance signal, converting the weak analog signal into a standard voltage signal. The signal processing unit then converts the voltage signal into a digital signal, which is transmitted to the data receiving module via the wireless communication unit.

[0020] Power supply module; The power supply module provides power to the wireless stress / strain microsensor, signal processing unit, and wireless communication unit; Analysis and processing terminal; The analysis and processing terminal includes a data receiving module, a data processing and analysis module, a prediction module, a storage module, an early warning module, and a display module; The wireless communication unit is electrically connected to the data receiving module. The data receiving module is used to receive data collected by the data acquisition module. The data processing and analysis module is used to process and analyze the received data and complete the assessment of the surrounding rock stability according to the preset assessment model. The display module is used to display the processing results. The prediction module is connected to the data processing and analysis module. The prediction module predicts the future stability trend of the surrounding rock based on the prediction model built by historical and real-time data. The data processing and analysis module includes a data preprocessing unit, a feature extraction unit, and a stability assessment unit. The data preprocessing unit is used to filter, reduce noise, and process outliers in the received data. The feature extraction unit is used to extract feature parameters related to the stability of the surrounding rock from the preprocessed data. The stability assessment unit includes an assessment model, which is used to assess the stability of the surrounding rock based on the feature parameters and the preset assessment model. The model optimization module is used to optimize and evaluate the model.

[0021] A method for real-time monitoring of surrounding rock stability based on distributed smart anchors includes the following steps: S1. Install the anchor body in the surrounding rock. Install multiple sets of anchor bodies according to the area of ​​the surrounding rock. Number the wireless stress / strain micro-sensors on each set of anchor bodies. Collect the stress / strain data of the corresponding anchor body in real time through the wireless stress / strain micro-sensors. The acquisition frequency of the wireless stress / strain micro-sensors can be set to 1 time / second. S2. The signal processing unit processes and converts the acquired stress / strain data to obtain a digital signal, which is then transmitted to the data receiving module via the wireless communication unit; the data receiving module then sends the digital signal to the data processing and analysis module. S3. The data preprocessing unit of the data processing and analysis module preprocesses the digital signal. Preprocessing includes filtering, noise reduction, and outlier removal. The mean method is used to filter the data and remove high-frequency noise. The 3σ criterion is used to identify and remove outliers; that is, when a data value deviates from the mean by more than three times the standard deviation, it is considered an outlier. The nearest neighbor substitution method is used to supplement the data, ensuring its integrity and accuracy. The feature extraction unit extracts features from the preprocessed data to obtain feature parameters, including the maximum, minimum, and average stress / strain values, rate of change, and cumulative change. These feature parameters are then input into a preset evaluation model for stability assessment. The stability assessment results are then sent to the display module for display. Simultaneously, the data is stored through the storage module. S4. Further analyze the data through the prediction module to generate a prediction of the stress / strain change trend for a future preset time period; input the predicted trend data into the data processing and analysis module, and obtain the prediction results of the surrounding rock stability within the expected time period according to step S3. S5. When the data processing and analysis module determines that the surrounding rock has an abnormal stability, it issues an early warning signal through the early warning module. When it predicts that a danger will occur, it outputs the expected time period of the danger and displays the number and location of the wireless stress / strain micro-sensor that has detected the abnormality in the display module, so as to facilitate the staff to conduct fixed-point inspections.

[0022] The following provides a further description of the construction of the pre-defined evaluation model; The assessment model is constructed using a machine learning algorithm. First, a large amount of historical monitoring data is collected to support the model. This historical data is based on extensive historical data collected by the system, including stress / strain data for each anchor bolt. It also correlates this data with the stability of the surrounding rock during the corresponding data collection period, indicating whether the rock support is stable, experiencing local deformation, or exhibiting anomalies. This ensures that subsequent data is matched with the stability status. Feature parameters are extracted from the stress / strain data (these are the same as those mentioned above). Then, a machine learning algorithm is used to construct the assessment model based on these feature parameters. The machine learning algorithm can employ decision trees, neural networks, etc. It trains the assessment model to learn the mapping relationship between the data and the surrounding rock stability by correlating the stability of the surrounding rock during the corresponding data collection period in the historical monitoring data. This allows the assessment model to output the corresponding surrounding rock stability assessment result based on the input real-time data.

[0023] During use, the evaluation model is optimized through the model optimization module. As the system runs for a long time, new data will be continuously collected. The model optimization module will use this new data as incremental samples to input into the evaluation model, so that the evaluation model can complete the optimization training and continuously adjust the parameters of the evaluation model.

[0024] A prediction model is built through a prediction module. The prediction model is constructed using a Long Short-Term Memory (LSTM) network algorithm and is trained based on historical stress / strain trend data. By learning from historical data changes, the prediction model can predict data changes in future time periods based on the input data.

[0025] The above descriptions are merely embodiments of the present invention, and common knowledge such as specific technical solutions and / or characteristics are not described in detail here. It should be noted that those skilled in the art can make various modifications and improvements without departing from the technical solutions of the present invention, and these should also be considered within the scope of protection of the present invention. These modifications and improvements will not affect the effectiveness of the implementation of the present invention or the practicality of the patent. The scope of protection claimed in this application should be determined by the content of its claims, and the specific embodiments described in the specification can be used to interpret the content of the claims.

Claims

1. A real-time monitoring system for surrounding rock stability based on distributed intelligent anchor bolts, characterized in that, include: Data acquisition module; The acquisition module includes an anchor bolt body, which is connected to a wireless stress / strain microsensor, a signal processing unit, and a wireless communication unit. The signal processing unit is electrically connected to the wireless stress / strain microsensor, and the wireless communication unit is electrically connected to the signal processing unit. Power supply module; The power supply module provides power to the wireless stress / strain microsensor, the signal processing unit, and the wireless communication unit. Display module; the display module is used to display the analysis and processing results; Analysis and processing terminal; the analysis and processing terminal includes a data receiving module, a data processing and analysis module, a prediction module, a storage module, and an early warning module; The wireless communication unit is electrically connected to the data receiving module. The data receiving module is used to receive data collected by the data acquisition module. The data processing and analysis module is used to process and analyze the received data and complete the assessment of the surrounding rock stability according to the preset assessment model. The prediction module is connected to the data processing and analysis module. The prediction module predicts the future stability trend of the surrounding rock based on the prediction model built by historical and real-time data. Model optimization module; the model construction and optimization module is used to optimize and evaluate the model.

2. The real-time monitoring system for surrounding rock stability based on distributed intelligent anchor bolts as described in claim 1, characterized in that, The wireless stress / strain microsensor is fabricated using carbon fiber and silicone elastomer as the main raw materials combined with micron-level processing technology.

3. The real-time monitoring system for surrounding rock stability based on distributed intelligent anchor bolts as described in claim 1, characterized in that, The wireless communication unit adopts low-power wide-area network communication technology, which enables multiple data acquisition modules to be infinitely networked and expanded.

4. The real-time monitoring system for surrounding rock stability based on distributed intelligent anchor bolts as described in claim 1, characterized in that, The data processing and analysis module includes a data preprocessing unit, a feature extraction unit, and a stability evaluation unit; the data preprocessing unit is used to filter, reduce noise, and process outliers in the received data. The feature extraction unit is used to extract feature parameters related to the stability of the surrounding rock from the preprocessed data; the stability assessment unit includes an assessment model, and the stability assessment unit is used to assess the stability of the surrounding rock based on the feature parameters and the preset assessment model.

5. A method for real-time monitoring of surrounding rock stability based on distributed intelligent anchor bolts, applied to the real-time monitoring system described in any one of claims 1-5, characterized in that, Includes the following steps: S1. Install the anchor body in the surrounding rock. Install multiple sets of anchor bodies according to the area of ​​the surrounding rock. Number the wireless stress / strain micro-sensors on each set of anchor bodies. Collect the stress / strain data of the corresponding anchor body in real time through the wireless stress / strain micro-sensors. S2. The acquired stress / strain data is processed and converted into a digital signal by the signal processing unit, and then transmitted to the data receiving module by the wireless communication unit. The data receiving module sends digital signals to the data processing and analysis module; S3. The data preprocessing unit of the data processing and analysis module preprocesses the digital signal. The preprocessing includes filtering, noise reduction and outlier removal of the data. The feature extraction unit extracts features from the preprocessed data to obtain feature parameters. The feature parameters are input into a preset evaluation model for stability evaluation. The stability evaluation results are then sent to the display module for display. At the same time, the data is stored through the storage module. S4. Further analyze the data through the prediction module to generate a prediction of the stress / strain change trend for a future preset time period; input the predicted trend data into the data processing and analysis module, and obtain the prediction results of the surrounding rock stability within the expected time period according to step S3. S5. When the data processing and analysis module determines that the surrounding rock has an abnormal stability, it issues an early warning signal through the early warning module. When it predicts that a danger will occur, it outputs the expected time period of the danger and displays the number and location of the wireless stress / strain micro-sensor that has detected the abnormality in the display module, so as to facilitate the staff to conduct fixed-point inspections.

6. The method for real-time monitoring of surrounding rock stability based on distributed intelligent anchor bolts as described in claim 5, characterized in that, In step S3, the mean method is used to filter the data and remove high-frequency noise, and the 3σ criterion is used to identify and remove outliers in the data.

7. The method for real-time monitoring of surrounding rock stability based on distributed intelligent anchor bolts as described in claim 5, characterized in that, The characteristic parameters in step S3 include the maximum, minimum, average, rate of change, and cumulative change of stress / strain.

Images