Tunneling process automation monitoring method

Abstract

The application discloses a tunnel construction process automatic monitoring method, and belongs to the technical field of tunnel engineering construction monitoring. The method comprises the following steps: step 1, automatic monitoring equipment is arranged at key positions of a tunnel opening area, an advanced support section, an excavation face, an initial support structure, a waterproof layer construction area and a secondary lining structure; step 2, each automatic monitoring equipment is started, and monitoring data is collected at a preset sampling frequency; step 3, after receiving the monitoring data, a central monitoring platform uses a big data analysis algorithm to deeply process the monitoring data; and step 4, the central monitoring platform feeds back monitoring results and early warning information after analysis to a tunnel construction control system in real time. The application realizes real-time data acquisition and analysis through 5G technology, especially the UWB positioning system collects data once per second, realizes instant acquisition and analysis of monitoring data, and compared with traditional manual monitoring, the data update frequency is improved by tens of times, and abnormal conditions in the construction process can be found in time.

Description

Technical Field

[0001] This invention relates to the field of tunnel construction monitoring technology, and more specifically, to an automated monitoring method for tunnel construction processes. Background Technology

[0002] During tunnel construction, monitoring each process is crucial for ensuring construction safety and controlling project quality. Tunnel construction involves complex procedures, encompassing multiple stages such as portal construction, pre-support, excavation, initial support, waterproofing layer construction, and secondary lining. The construction status of each stage requires precise monitoring to guide subsequent operations.

[0003] In existing technologies, tunnel construction monitoring largely relies on manual operation. For example, in monitoring surrounding rock deformation, technicians need to periodically go to the site to collect data using equipment such as total stations and levels. This is not only time-consuming and labor-intensive, but also results in long data collection intervals, making it difficult to reflect the dynamic changes of the surrounding rock in real time. In terms of supporting structure stress monitoring, traditional methods mostly use wired sensors, which involve complex wiring and are easily affected by construction interference. The data transmission stability is poor, and data loss or delays often occur. For monitoring the condition of the excavation face, it mainly relies on manual inspection, which is highly subjective and prone to overlooking safety hazards due to human negligence.

[0004] Traditional tunnel monitoring methods, while introducing some automated equipment, have limited monitoring scope and fail to cover all tunnel construction processes. Furthermore, the lack of data interaction and linkage between various monitoring devices makes it impossible to form a unified monitoring and management system, which is insufficient to meet the demands of modern tunnel construction for efficient and accurate monitoring.

[0005] In view of this, we propose an automated monitoring method for tunnel construction processes. Summary of the Invention

[0006] The purpose of this invention is to provide an automated monitoring method for tunnel construction processes to solve the problems mentioned in the background section.

[0007] To achieve the above objectives, the present invention provides the following technical solution: The automated monitoring method for tunnel construction includes the following steps: Step 1: Deployment and Installation of Monitoring Points and Equipment for the Entire Tunnel Construction Process: Based on the characteristics of each stage of tunnel construction, automated monitoring equipment is deployed at key locations including the tunnel entrance area, the advanced support section, the excavation face, the initial support structure, the waterproofing layer construction area, and the secondary lining structure. Specifically, UWB base stations are set up around the tunnel entrance, and UWB positioning cards are worn by personnel and equipment involved in the tunnel entrance construction. Distributed fiber optic sensors are installed in the advanced support section. High-definition cameras and infrared thermal imagers are deployed at the excavation face. Vibrating wire sensors are embedded inside the initial support structure and the secondary lining structure. Humidity sensors are installed in the waterproofing layer construction area. All automated monitoring equipment is connected to the central monitoring platform via wireless transmission modules. Step 2: Real-time acquisition and transmission of monitoring data: Start each automated monitoring device and collect monitoring data according to the preset sampling frequency; after the collected monitoring data is processed by the device's built-in preprocessing module, it is transmitted to the central monitoring platform in real time through 5G wireless communication technology; Step 3: Intelligent Analysis and Early Warning of Monitoring Data: After receiving the monitoring data, the central monitoring platform uses big data analysis algorithms to perform in-depth processing of the monitoring data. Specifically, this includes: trend analysis of displacement and location data acquired by the UWB positioning system; parsing of distributed fiber optic sensor data; processing of high-definition images of the excavation face using image recognition algorithms; analysis of data from vibrating wire sensors; and judgment of the waterproof layer construction quality based on humidity sensor data. When any monitoring data exceeds a preset threshold, the central monitoring platform automatically issues an early warning signal. Step 4: Linking monitoring data with construction procedures for adjustment: The central monitoring platform feeds back early warning information and analysis results to the tunnel construction control system to drive real-time adjustment of construction parameters and automatically archive monitoring data and adjustment records.

[0008] Preferably, in step 1, the preset sampling frequency is as follows: the UWB positioning system collects data once per second, the distributed fiber optic sensor collects data once every 5 minutes, and the high-definition camera collects images in real time.

[0009] Preferably, in step 2, the preprocessing module processes the monitoring data by filtering noise and converting formats.

[0010] Preferably, in step 3, the image recognition algorithm processes the high-definition image of the excavation face by: identifying the lithology and fracture development of the excavation face, and identifying whether there are abnormal phenomena such as water inrush or mud outrush at the excavation face.

[0011] Preferably, in step 3, after the central monitoring platform issues an early warning signal, the early warning information is simultaneously pushed to relevant management personnel through the sound and light alarm device and the mobile APP.

[0012] Preferably, in step 4, when the monitoring data of surrounding rock displacement, stress and other stability-related data at the excavation face are lower than the preset threshold, the construction control system adjusts the construction procedure in the following ways: reducing the excavation advance and optimizing the blasting parameters.

[0013] Preferably, in step 4, when the initial support structure stress exceeds the threshold, the construction control system adjusts the construction procedure by increasing the amount of support material or adjusting the support method.

[0014] Preferably, in step 1, if the reference signal received power (RSRP) of the 5G signal in the tunnel remains below -110dBm for 10 minutes, the wireless transmission module uses a leaky cable communication method instead of 5G wireless communication.

[0015] Preferably, in step 3, if the data analysis accuracy of the initial big data analysis algorithm model is less than 85% for five consecutive working days, the monitoring data is processed by a combination of manual analysis and algorithm self-learning. In this process, the algorithm analysis results are reviewed and corrected by a person skilled in the field of tunnel engineering monitoring and data processing, and the algorithm improves its self-analysis accuracy by learning from the experience of manual correction.

[0016] Preferably, in step 1, if the monitoring of the excavation face image only requires the identification of macroscopic features, such as the overall lithology, obvious cracks larger than 50mm, and large areas of water inrush, and the image resolution requirement is 1280×720 pixels or less, the high-definition camera is replaced with an ordinary network camera.

[0017] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. Improved real-time monitoring: Each monitoring device collects data in real time and transmits it through 5G technology. In particular, the UWB positioning system collects data once per second, enabling instant acquisition and analysis of monitoring data. Compared with traditional manual monitoring, the data update frequency is increased by dozens of times, which can promptly detect abnormalities in the construction process.

[0018] 2. Improve data accuracy: Automated monitoring equipment avoids subjective errors caused by manual operation, the UWB positioning system has high positioning accuracy, and the data preprocessing module and intelligent analysis algorithm further improve the reliability of the data, providing accurate basis for construction decisions.

[0019] 3. Achieve full coverage of all processes: The monitoring points cover all processes of tunnel construction. Combined with the UWB positioning system for monitoring personnel, equipment and tunnel entrance areas, a complete monitoring system is formed, ensuring that there are no blind spots in the monitoring during construction and fully guaranteeing construction safety.

[0020] 4. Promote collaborative optimization of work processes: The linkage between monitoring data and construction procedures enables each process to be flexibly adjusted according to the actual situation, reducing resource waste and safety risks caused by blind construction, improving construction efficiency and reducing project costs. Detailed Implementation

[0021] The technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0022] Example: The automated monitoring method for tunnel construction includes the following steps: Step 1: Deployment and Installation of Monitoring Points and Equipment for the Entire Tunnel Construction Process: Based on the characteristics of each stage of tunnel construction, automated monitoring equipment is deployed at key locations including the tunnel entrance area, the advanced support section, the excavation face, the initial support structure, the waterproofing layer construction area, and the secondary lining structure. Specifically, UWB base stations are set up around the tunnel entrance, and UWB positioning cards are worn by personnel and equipment involved in the tunnel entrance construction. Distributed fiber optic sensors are installed in the advanced support section. High-definition cameras and infrared thermal imagers are deployed at the excavation face. Vibrating wire sensors are embedded inside the initial support structure and the secondary lining structure. Humidity sensors are installed in the waterproofing layer construction area. All automated monitoring equipment is connected to the central monitoring platform via wireless transmission modules. Specifically, in step 1, the preset sampling frequency is as follows: the UWB positioning system collects data once per second, the distributed fiber optic sensor collects data once every 5 minutes, and the high-definition camera collects images in real time.

[0023] If the Reference Received Power (RSRP) of the 5G signal in the tunnel remains below -110 dBm for 10 consecutive minutes, the wireless transmission module will use a leaky cable communication method instead of 5G wireless communication. The leaky cable used is a segmented, tapered, non-uniform slotted leaky coaxial cable that conforms to the international standard IEC 61196-1-127:2024. Its transmission performance is evaluated using a link loss test method.

[0024] If the monitoring of excavation face images only requires the identification of macroscopic features, such as overall lithology, obvious cracks larger than 50mm, large areas of water inrush, and the image resolution requirement is 1280×720 pixels or less, then the high-definition camera should be replaced with a regular network camera.

[0025] In this application, in step 1, the distributed fiber optic sensors are installed at a density of 32 monitoring points per square meter, with a data refresh rate of 200 times per second. They measure, analyze, and locate vibrations, strain, and temperature around the fiber optic cable using principles such as Rayleigh scattering and Brillouin scattering. Vibrating wire sensors are specifically implanted in the arch crown and arch waist of the initial support structure and secondary lining structure to monitor the structure's temperature, stress, and displacement in real time.

[0026] Step 2: Real-time acquisition and transmission of monitoring data: Start each automated monitoring device and collect monitoring data according to the preset sampling frequency; after the collected monitoring data is processed by the device's built-in preprocessing module, it is transmitted to the central monitoring platform in real time through 5G wireless communication technology; Specifically, in step 2, the preprocessing module processes the monitoring data, including filtering noise and format conversion.

[0027] Step 3: Intelligent Analysis and Early Warning of Monitoring Data: After receiving the monitoring data, the central monitoring platform uses big data analysis algorithms to perform in-depth processing of the monitoring data. Specifically, this includes: trend analysis of displacement and location data acquired by the UWB positioning system; parsing of distributed fiber optic sensor data; processing of high-definition images of the excavation face using image recognition algorithms; analysis of data from vibrating wire sensors; and judgment of the waterproof layer construction quality based on humidity sensor data. When any monitoring data exceeds a preset threshold, the central monitoring platform automatically issues an early warning signal. Specifically, in step 3, the image recognition algorithm processes the high-definition image of the excavation face by identifying the lithology and fracture development of the excavation face, as well as identifying whether there are abnormal phenomena such as water inrush or mud outburst at the excavation face.

[0028] After the central monitoring platform issues an early warning signal, the warning information is simultaneously pushed to relevant management personnel through audible and visual alarm devices and a mobile APP.

[0029] If the initial data analysis accuracy of the big data analytics algorithm model is below 85% for five consecutive working days, a combination of manual analysis and algorithm self-learning is used to process the monitoring data. Specifically, experts with expertise in tunnel engineering monitoring and data processing review and correct the algorithm's analysis results, allowing the algorithm to improve its accuracy by learning from manual corrections. Through this "manual analysis + algorithm self-learning" model, after three months of iterative optimization, the data analysis accuracy of the big data analytics algorithm model can be improved from below 85% to above 95%, effectively enhancing the accuracy and efficiency of monitoring data processing.

[0030] In this application, step 3 sets differentiated preset thresholds for surrounding rocks of different lithologies: for hard rock formations, an early warning is triggered when the displacement rate of the surrounding rock exceeds 1.5 mm / h; for soft rock formations, an early warning is triggered when the displacement rate of the surrounding rock exceeds 3 mm / h. The stress threshold for hard rock formations is set to 80% of the rock compressive strength, and the stress threshold for soft rock formations is set to 60% of the rock compressive strength.

[0031] Step 4: Linking monitoring data with construction procedures for adjustment: The central monitoring platform will feed back the analyzed monitoring results and early warning information to the tunnel construction control system in real time. The tunnel construction control system will adjust the construction procedures based on the monitoring results and early warning information. At the same time, the central monitoring platform will record the monitoring data and adjustment status of each procedure to form a construction monitoring archive.

[0032] In this application, the central monitoring platform adopts a standardized data storage structure, follows a data standardization framework similar to the CIMISS system, and standardizes the naming, format, and algorithms of various data types to achieve integrated management of real-time and historical monitoring data. Monitoring data is stored in JSON format to ensure data consistency and scalability.

[0033] Specifically, in step 4, when the monitoring data of surrounding rock displacement, stress and other stability-related data at the excavation face are lower than the preset threshold, the construction control system adjusts the construction procedure in the following ways: reducing the excavation advance and optimizing the blasting parameters.

[0034] In this application, in step 4, when the initial support structure stress exceeds the threshold, the construction control system adjusts the construction procedure by increasing the amount of support material or adjusting the support method.

[0035] In this application, all automated monitoring equipment is calibrated every 30 days. A standard signal source is used to verify the performance of the sensors to ensure the accuracy of the monitoring data. The calibration results are automatically uploaded to the central monitoring platform to form calibration records. In this application, the monitoring data is encrypted using the AES-256 encryption algorithm during transmission. The central monitoring platform has multiple access levels, and only authorized personnel can view and process sensitive monitoring data, thus ensuring data security.

[0036] In this application, in step 2, when an automated monitoring device malfunctions, the system automatically switches to the backup device and notifies maintenance personnel to perform repairs via an audible and visual alarm. Simultaneously, the system employs a data interpolation algorithm to appropriately supplement missing data during the malfunction period, ensuring the continuity of data analysis. In this application, by adopting the above-mentioned automated monitoring method for tunnel construction processes, the incidence of tunnel construction safety accidents can be reduced by more than 30% and the construction efficiency can be increased by 15%-20% in actual engineering applications, significantly saving construction costs and time.

[0037] In this application, the humidity sensor installed in the waterproof layer construction area in step 1 uses the ambient humidity plus the interlayer humidity difference as the core indicator for judging the sealing performance: when the ambient humidity in the waterproof layer construction area exceeds 65% for 2 consecutive hours, or the humidity difference between the inner side (near the initial support side) and the outer side (near the secondary lining side) of the waterproof layer is less than 5% for 1 consecutive hour, the waterproof layer is judged to be unqualified for sealing. At this time, the process linkage adjustment in step 4 is triggered, the construction control system automatically suspends the subsequent laying, welding and other operations of the waterproof layer, and generates an inspection instruction to prompt the construction personnel to check the sealing performance of the waterproof layer joints, damage and the dryness of the base layer. Construction can only be restarted after the humidity monitoring data returns to the qualified range (ambient humidity ≤ 65% and interlayer humidity difference ≥ 5%).

[0038] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely preferred examples and are not intended to limit the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. An automated monitoring method for tunnel construction processes, characterized in that, Includes the following steps: Step 1: Deployment and Installation of Monitoring Points and Equipment for the Entire Construction Process: Based on the characteristics of each construction process in the tunnel, automated monitoring equipment is deployed at key locations including the tunnel entrance area, the advanced support section, the excavation face, the initial support structure, the waterproofing layer construction area, and the secondary lining structure. Specifically, UWB base stations are set up around the tunnel entrance, and UWB positioning cards are worn by personnel and equipment involved in the tunnel entrance construction. Distributed fiber optic sensors are installed in the advanced support section. High-definition cameras and infrared thermal imagers are deployed at the excavation face. Vibrating wire sensors are embedded inside the initial support structure and the secondary lining structure. Humidity sensors are installed in the waterproofing layer construction area. All the automated monitoring equipment is connected to the central monitoring platform via a wireless transmission module. The preset sampling frequency is as follows: the UWB positioning system collects data once per second, the distributed fiber optic sensors collect data once every 5 minutes, and the high-definition cameras collect images in real time. Step 2, Real-time acquisition and transmission of monitoring data: Start each of the automated monitoring devices and collect monitoring data at the preset sampling frequency; after the collected monitoring data is processed by the preprocessing module, it is transmitted to the central monitoring platform via 5G wireless communication; if the reference signal receiving power of the 5G signal in the tunnel is below -110dBm for 10 minutes, the wireless transmission module will use a leaky cable communication method instead of 5G wireless communication. Step 3: Intelligent Analysis and Early Warning of Monitoring Data: After receiving the monitoring data, the central monitoring platform performs in-depth processing of the monitoring data using big data analysis algorithms. Specifically, this includes: trend analysis of displacement and location data acquired by the UWB positioning system; parsing of distributed fiber optic sensor data; processing of high-definition images of the excavation face using image recognition algorithms; and processing of the lithology and fracture development of the excavation face, as well as the presence of abnormal phenomena such as water inrush or mudslides. The platform also analyzes data from vibrating wire sensors and judges the construction quality of the waterproofing layer based on humidity sensor data. When any of the monitoring data exceeds a preset threshold, the central monitoring platform automatically issues an early warning signal. If the data analysis accuracy of the initial big data analysis algorithm model is below 85% for five consecutive working days, the monitoring data will be processed using a combination of manual analysis and algorithm self-learning. Specifically, the algorithm analysis results will be reviewed and corrected by a person skilled in tunnel engineering monitoring and data processing, and the algorithm will improve its self-analysis accuracy by learning from the experience of manual correction. Step 4: Linking monitoring data with construction procedures for adjustment: The central monitoring platform feeds back early warning information and analysis results to the tunnel construction control system to drive real-time adjustment of construction parameters and automatically archive monitoring data and adjustment records.

2. The automated monitoring method for tunnel construction processes according to claim 1, characterized in that: In step 2, the preprocessing module processes the monitoring data, including noise filtering and format conversion.

3. The automated monitoring method for tunnel construction processes according to claim 1, characterized in that: In step 3, after the central monitoring platform issues an early warning signal, the early warning information is simultaneously pushed to relevant management personnel through the sound and light alarm device and the mobile APP.

4. The automated monitoring method for tunnel construction processes according to claim 1, characterized in that: In step 4, when the monitoring data of surrounding rock displacement, stress and other stability-related data are lower than the preset threshold, the construction control system adjusts the construction procedure by reducing the excavation advance and optimizing the blasting parameters.

5. The automated monitoring method for tunnel construction processes according to claim 1, characterized in that: In step 4, when the initial support structure stress exceeds the threshold, the construction control system adjusts the construction procedure by increasing the amount of support material or adjusting the support method.

6. The automated monitoring method for tunnel construction processes according to claim 1, characterized in that: In step 1, if the monitoring of the excavation face image only requires the identification of macroscopic features, overall lithology, obvious cracks larger than 50mm, large areas of water inrush, and the image resolution requirement is 1280×720 pixels or less, the high-definition camera is replaced with an ordinary network camera.