Intelligent rock tunnel supporting system and method adaptive to geological conditions

Abstract

The invention discloses a rock tunnel intelligent supporting system and method adaptive to geological conditions, and relates to the technical field of tunnel construction automation and intellectualization. The system comprises an intelligent advanced geological forecast module, an intelligent surrounding rock quality evaluation system, a self-adaptive support design optimization module, an intelligent construction equipment monitoring system, an environment monitoring module, a safety early warning system, a construction data analysis and decision support system, a material supply chain management module, a personnel positioning and management system and an integrated control system. Through real-time monitoring and analysis of the intelligent advanced geological forecast module and the safety early warning system, potential geological risks and safety threats in the tunnel construction process can be found in time. And through an adaptive support design optimization algorithm, support parameters and a construction scheme can be dynamically adjusted according to real-time geological data and a surrounding rock quality evaluation result. The integrated control system serves as the core of the whole intelligent supporting system, and unified management and coordination of all the sub-modules are achieved.

Description

Technical Field

[0001] The present application relates to the technical field of tunnel construction automation and intelligence, and in particular to an intelligent rock tunnel support system and method that is adaptive to geological conditions. Background Art

[0002] With the development of modern engineering construction, tunnel engineering, as an important transportation and municipal infrastructure, has become increasingly problematic in terms of construction safety and efficiency under complex geological conditions. Traditional tunnel support methods mainly rely on engineers’ experience and on-site manual inspections, which are not only inefficient but also difficult to cope with rapidly changing geological conditions and construction environments, posing significant safety risks.

[0003] In order to improve the safety and efficiency of tunnel construction, the industry has begun to explore the application of intelligent technology in recent years. However, most of the existing intelligent support systems are in the research and development or small-scale trial stage, and have not yet formed a mature, comprehensive solution that can be commercialized on a large scale. In addition, the tunnel construction process involves a variety of complex subsystems. There is a serious data island phenomenon between these subsystems, and there is a lack of effective integration and coordination, which limits the improvement of the intelligent level of tunnel construction. Summary of the invention

[0004] The purpose of this application is to provide a rock tunnel intelligent support system and method that is adaptive to geological conditions, which can realize automation and intelligence of tunnel construction, with high integration, fast response speed and strong adaptability.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In the first aspect, the present application provides an intelligent support system for rock tunnels with adaptive geological conditions, the intelligent support system for rock tunnels with adaptive geological conditions comprising: an intelligent advanced geological prediction module, an intelligent surrounding rock quality evaluation system, an adaptive support design optimization module, an intelligent construction equipment monitoring system, an environmental monitoring module, a safety early warning system, a construction data analysis and decision support system, a material supply chain management module, a personnel positioning and management system, and an integrated control system;

[0007] The intelligent advanced geological prediction module is used to: obtain the geological data of the tunnel face, and use the deep learning network to predict the probability and risk level of geological changes based on the geological data of the tunnel face;

[0008] The intelligent surrounding rock quality evaluation system is used to: obtain surrounding rock data at the tunnel perimeter and calculate the surrounding rock quality index based on the surrounding rock data;

[0009] The adaptive support design optimization module is used to: obtain the surrounding rock quality index and recommend the required support scheme according to the surrounding rock quality index;

[0010] The intelligent construction equipment monitoring system is used to: obtain the operating parameters of the construction equipment and issue an alarm when the operating parameters exceed a first preset threshold;

[0011] The environment monitoring module is used to: obtain the environment parameters inside the tunnel and issue an alarm when the environment parameters exceed a second preset threshold;

[0012] The safety warning system is used to:

[0013] Acquiring safety monitoring parameters; the safety monitoring parameters include: operating parameters of the construction equipment and environmental parameters inside the tunnel;

[0014] Using pattern recognition methods to identify whether the safety monitoring parameters have potential safety risks based on a historical case database;

[0015] The construction data analysis and decision support system is used for:

[0016] Obtain data from the intelligent construction equipment monitoring system, environmental monitoring module and safety early warning system to obtain safety data;

[0017] Obtain construction progress, material usage and worker activity data to obtain construction data;

[0018] predicting construction trends using historical construction data in combination with the safety data and the construction data;

[0019] The material supply chain management system is used for:

[0020] Obtain inventory levels and supply chain status of materials needed for construction projects;

[0021] Use intelligent forecasting algorithms to predict future material needs based on material consumption rates and inventory levels;

[0022] Generate a purchase order based on the future material demand and the inventory level, and send the order information to the supplier through electronic data interchange technology;

[0023] The personnel positioning and management system is used to: obtain the location information of each person and send an alarm to the person when the person approaches a dangerous area or exceeds a preset safety range;

[0024] The integrated control system is used to coordinate and control the information sharing and collaborative work among the modules.

[0025] In a second aspect, the present application provides a rock tunnel intelligent support method that is adaptive to geological conditions, and the rock tunnel intelligent support method that is adaptive to geological conditions includes:

[0026] Acquire tunnel face geological data, and use a deep learning network to predict the probability and risk level of geological changes based on the tunnel face geological data;

[0027] Acquiring surrounding rock data at the tunnel perimeter, and calculating a surrounding rock quality index based on the surrounding rock data;

[0028] Obtaining the surrounding rock quality index, and recommending a required support scheme according to the surrounding rock quality index;

[0029] Acquiring operating parameters of the construction equipment, and providing an alarm when the operating parameters exceed a first preset threshold;

[0030] Acquiring environmental parameters inside the tunnel, and issuing an alarm when the environmental parameters exceed a second preset threshold;

[0031] Acquiring safety monitoring parameters; the safety monitoring parameters include: operating parameters of the construction equipment and environmental parameters inside the tunnel;

[0032] Using pattern recognition methods to identify whether the safety monitoring parameters have potential safety risks based on a historical case database;

[0033] Obtain data from the intelligent construction equipment monitoring system, environmental monitoring module and safety early warning system to obtain safety data;

[0034] Obtain construction progress, material usage and worker activity data to obtain construction data;

[0035] predicting construction trends using historical construction data in combination with the safety data and the construction data;

[0036] Obtain inventory levels and supply chain status of materials needed for construction projects;

[0037] Use intelligent forecasting algorithms to predict future material needs based on material consumption rates and inventory levels;

[0038] Generate a purchase order based on the future material demand and the inventory level, and send the order information to the supplier through electronic data interchange technology;

[0039] The location information of each person is obtained, and an alarm is sent to the person when the person approaches a dangerous area or exceeds a preset safety range.

[0040] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0041] The present application provides an intelligent support system and method for rock tunnels with adaptive geological conditions, and the system includes: an intelligent advanced geological prediction module, an intelligent surrounding rock quality evaluation system, an adaptive support design optimization module, an intelligent construction equipment monitoring system, an environmental monitoring module, a safety warning system, a construction data analysis and decision support system, a material supply chain management module, a personnel positioning and management system, and an integrated control system; the intelligent advanced geological prediction module is used to obtain the geological data of the tunnel face, and use a deep learning network to predict the probability and risk level of geological changes based on the geological data of the tunnel face; the intelligent surrounding rock quality evaluation system is used to obtain the surrounding rock data at the tunnel perimeter, and calculate the surrounding rock quality index based on the surrounding rock data; the adaptive support design optimization module is used to obtain the surrounding rock quality index, and recommend the required support scheme based on the surrounding rock quality index; the intelligent construction equipment monitoring system is used to obtain the operating parameters of the construction equipment, and alarm when the operating parameters exceed a first preset threshold; the environmental monitoring module is used to obtain the environmental parameters inside the tunnel, and alarm when the environmental parameters exceed a second preset threshold; the safety warning system is used to obtain safety monitoring parameters; the safety monitoring parameters include: The operation parameters of the construction equipment and the environmental parameters inside the tunnel are used; the pattern recognition method is used to identify whether the safety monitoring parameters have potential safety risks based on the historical case database; the construction data analysis and decision support system is used to: obtain data from the intelligent construction equipment monitoring system, the environmental monitoring module and the safety early warning system to obtain safety data; obtain construction progress, material usage and worker activity data to obtain construction data; use historical construction data combined with the safety data and the construction data to predict construction trends; the material supply chain management system is used to: obtain the inventory level and supply chain status of materials required in the construction project; use intelligent prediction algorithms to predict future material needs based on material consumption rates and inventory levels; generate purchase orders based on the future material needs and inventory levels, and send order information to suppliers through electronic data exchange technology; the personnel positioning and management system is used to: obtain the location information of each person, and send an alarm to the person when the person approaches a dangerous area or exceeds a preset safety range; the integrated control system is used to coordinate and control information sharing and collaborative work between modules. Through the collaboration and cooperation between these modules, the automation and intelligence of tunnel construction can be realized, with high integration, fast response speed and strong adaptability. In addition, this application can improve construction safety: through real-time monitoring and analysis of the intelligent advanced geological prediction module and the safety early warning system, potential geological risks and safety threats in the tunnel construction process can be discovered in a timely manner. These systems use advanced prediction algorithms and historical data learning to warn of possible disasters such as landslides and rock bursts, thereby significantly reducing the incidence of construction accidents and ensuring the safety of construction personnel and equipment.Ability to optimize construction efficiency: The adaptive support design optimization algorithm can dynamically adjust support parameters and construction plans based on real-time geological data and surrounding rock quality evaluation results. This intelligent design process not only shortens the design cycle, but also improves the adaptability and reliability of the support structure, reduces construction delays and material waste caused by improper design, and significantly improves construction efficiency and economic benefits. It can also strengthen construction process management: The integrated control system, as the core of the entire intelligent support system, realizes unified management and coordination of all submodules. Through data integration and intelligent decision support, all aspects of the construction process, such as material supply, personnel management, and environmental monitoring, can be automated and intelligently controlled. This refined management method not only improves the transparency and controllability of the construction process, but also further enhances the overall efficiency and response speed of the construction process by optimizing resource allocation and process coordination. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 A system block diagram of a rock tunnel intelligent support system that is adaptive to geological conditions provided in one embodiment of the present application;

[0044] Figure 2 A schematic flow chart of a rock tunnel intelligent support method that is adaptive to geological conditions provided in one embodiment of the present application. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0046] The present application provides an intelligent support system and method for rock tunnels that is adaptive to geological conditions, aiming to improve the safety and efficiency of tunnel construction. The system adopts an intelligent advanced geological prediction module, combined with geophysical detection technology and deep learning algorithms, to achieve real-time prediction of the geological conditions ahead of tunnel construction. Through the intelligent surrounding rock quality evaluation system, the surrounding rock quality is automatically evaluated using multi-source data fusion technology. The core of this application lies in the adaptive support design optimization algorithm, which is based on artificial intelligence technology and dynamically optimizes support design parameters to adapt to real-time changing geological data. It also includes an intelligent construction equipment monitoring system, which uses the Internet of Things technology to monitor the status of construction equipment in real time, and realizes fault warning and automatic control through big data mining. In particular, the present application uses digital twin technology to create a digital twin model of tunnel construction, realizing the rapid collection and processing of geological information and real-time updating of support design.

[0047] The purpose of this application is to provide an intelligent rock tunnel support system that is adaptive to geological conditions and can respond to geological changes in real time, automatically adjust support strategies, and improve construction safety and efficiency.

[0048] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0049] In an exemplary embodiment, Figure 1 As shown, an intelligent support system for rock tunnels that is adaptive to geological conditions is provided, including: an intelligent advanced geological prediction module, an intelligent surrounding rock quality evaluation system, an adaptive support design optimization module, an intelligent construction equipment monitoring system, an environmental monitoring module, a safety early warning system, a construction data analysis and decision support system, a material supply chain management module, a personnel positioning and management system, and an integrated control system.

[0050] The intelligent advanced geological prediction module is used to obtain tunnel face geological data and use a deep learning network to predict the probability and risk level of geological changes based on the tunnel face geological data.

[0051] The intelligent advanced geological prediction module performs its functions according to the following specific steps: First, the deployed geophysical detection device collects high-precision geological parameters, including rock stress, wave velocity, electromagnetic characteristics, etc., at intervals of 1 meter within 50 meters in front of the tunnel face. These data are updated once a second. The collected data are sent to the central processing unit in real time at a transmission rate of 10 megabits per second through an encrypted wireless data transmission network. In the central processing unit, the data is first preprocessed, including removing noise and outliers, and then normalized to ensure that the data has a uniform scale in the range of -1 to 1. Then, a deep learning analysis of the data is performed every 5 seconds using a database containing more than 100,000 historical geological events to identify geological patterns and predict potential risks. First, the collected geological data needs to be preprocessed, which includes steps such as noise removal, outlier processing, data standardization and normalization. The purpose of preprocessing is to improve the quality of the data and make it suitable for deep learning analysis. Using a deep learning model, a convolutional neural network (CNN) automatically extracts features from the preprocessed data, which may include key geological parameters such as the physical properties of rocks, geological structures, and groundwater distribution. Pattern recognition is performed on geological parameter data by training a deep learning model, such as a deep neural network (DNN). This may involve using a large amount of historical geological event data to train the model so that it can recognize different geological patterns, such as rock types, faults, and fracture development. After identifying the geological pattern, the deep learning model can be further used to predict potential risks. This may include predicting geological changes and potential risks that may be encountered ahead of tunnel construction, such as landslides, rock bursts, and groundwater inrush. In some cases, geomechanical information constraints are introduced to improve the prediction accuracy of the deep learning model. For example, by simplifying the geomechanical equations and establishing physical constraint regularization terms, the ability to reason and interpret unknown data can be improved. The deep learning model is trained and validated using a historical geological event database. This database may contain more than 100,000 historical geological events and is used to train the model to identify geological patterns and predict risks. Deep learning analysis is usually performed dynamically and can be updated every 5 seconds to respond to geological changes in real time. This requires the model to process data quickly and provide instant prediction results. In some advanced applications, multiple data sources such as geophysical detection data, geological radar data, and seismic wave velocity measurement data are also integrated to obtain more comprehensive geological information. The deep neural network model uses a convolutional neural network structure of more than 100 layers in this process for feature learning and risk assessment. Ultimately, the forecast results include the probability and risk level of geological changes. Collect historical geological event data, including but not limited to rock types, faults, fissures, groundwater levels, geostress, etc. Collect environmental data related to geological changes, such as seismic activity, hydrogeological data, etc.Identify key factors that influence geological changes, such as physical and mechanical properties of rocks, geological structures, etc. Select statistical and geophysical parameters that are strongly correlated with geological changes as model input features. Use historical geological data to train machine learning models, such as random forests, support vector machines (SVMs), or deep neural networks (DNNs). Apply cross-validation and adjust model parameters to optimize model performance. Use the trained model to predict new geological data and estimate the probability of a specific geological change. For example, through the output layer of the deep learning model, a continuous value can be obtained, indicating the probability of a specific geological change. Define different levels of risk based on the probability of a geological change and the possible impact. Generally, the risk level can be divided into a combination of probability of occurrence and impact, such as low risk, medium risk, high risk, and very high risk. Use an independent validation set to test the prediction accuracy of the model. Adjust the model parameters and risk level classification criteria based on actual geological events.

[0052] Geological changes can include, but are not limited to, the following: Rock fractures and collapses, which are caused by geostress, groundwater activity, or tectonic activity. Rock bursts, where high-stress rocks suddenly release energy during tunnel excavation, causing rock fragments to be ejected rapidly. Groundwater surges, where aquifers in the rock formation are penetrated, causing large amounts of groundwater to flow into the tunnel. Geostress changes, where crustal movement causes changes in geostress around the tunnel, which may affect the stability of the tunnel. Fault activity, where fault displacement caused by earthquakes or tectonic activity may cause damage to the tunnel structure. Estimate the likelihood of specific geological changes based on historical data and model predictions. Assess the possible impacts of geological changes on tunnel construction and operation, such as casualties, equipment damage, and construction delays. Consider whether the geological changes can be detected by existing monitoring systems. Assess whether it is possible to mitigate or avoid the impacts of geological changes through engineering measures.

[0053] Risk levels are divided into the following ways: low risk, low probability of occurrence, small potential impact, easy to detect and control. Medium risk, medium probability of occurrence, controllable potential impact, certain monitoring and preventive measures are required. High risk, high probability of occurrence, serious potential impact, need to strengthen monitoring and take preventive measures. Extremely high risk, high probability of occurrence, catastrophic potential impact, need to take emergency measures immediately. The user interface is displayed in graphical and numerical form, for example, showing 'Probability of rock fracture zone: 75%, it is recommended to increase the support level to level III', and when the risk exceeds the preset threshold, such as the stability index is lower than 3.5, the stability index is a key indicator in tunnel engineering, which is used to quantify the stability of the tunnel surrounding rock. This index is usually calculated by comprehensively analyzing a variety of geological parameters that affect the stability of the surrounding rock, such as the uniaxial compressive strength, elastic modulus, crack density, ground stress and groundwater level of the rock. To obtain this index, engineers use statistical analysis or machine learning models, combined with historical data and field monitoring data, to establish a mathematical model that can reflect the stability of the surrounding rock; in actual application, once the stability index is calculated, it is compared with a pre-set threshold. For example, if the stability index is lower than 3.5, this may mean that the surrounding rock is not stable enough and there is a potential risk of collapse or rock burst. In this case, the automatic alarm system will be triggered to remind the construction team to take corresponding preventive measures, such as strengthening support or adjusting the construction plan. The forecast results are not limited to the stability index, but also include a series of information related to geological risks. This may include the probability of geological changes ahead of tunnel construction, risk level, recommended engineering measures, and alarm information. These results are usually presented in a visual way, such as charts, color coding or 3D models, so that engineers can intuitively understand the geological conditions and potential risks. In addition, the forecast results are updated regularly to reflect the real-time changes in geological conditions and ensure the timeliness and accuracy of construction decisions. The alarm system is automatically triggered to notify the construction team to take preventive measures immediately. This process ensures the accuracy of geological forecasts and the timeliness of construction responses.

[0054] The intelligent surrounding rock quality evaluation system is used to obtain surrounding rock data at the tunnel perimeter and calculate the surrounding rock quality index based on the surrounding rock data.

[0055] The operation process of the intelligent surrounding rock quality evaluation system is as follows: the system activates the multi-source data acquisition unit, deploys geological radar and seismic wave velocity measurement equipment, and collects data every 0.5 meters around the tunnel at a frequency of 10 seconds to monitor the density, humidity, compressive strength and other key parameters of the surrounding rock in real time. The collected data is transmitted to the central processing station through a high-speed optical fiber network at a rate of at least 1 gigabit per second. At the central processing station, the data is first pre-processed, including using a bandpass filter to remove 99% of high-frequency noise and low-frequency drift, and then normalized from 0 to 1 to ensure that the data is analyzed on a unified scale. The data fusion processing unit uses advanced fuzzy C-means clustering algorithm and adaptive neural network to comprehensively evaluate the normalized data and calculate the surrounding rock quality index (RMQI). The calculation of the surrounding rock quality index (RMQI) depends on multiple key geological data, including the uniaxial compressive strength (UCS) of the rock, crack density, joint spacing (Jn), rock roughness (Jr), groundwater conditions (Jw) and ground stress (σ). Data can be obtained through field geological surveys, borehole tests, and laboratory tests. The process of calculating RMQI usually begins with the quantification of these parameters. The uniaxial compressive strength of the rock can be obtained through laboratory tests, while the crack density and joint spacing are usually evaluated on site by geological engineers. The effects of rock roughness and groundwater conditions can be quantified through field observations and historical data. The specific calculation process often uses the following formula to estimate the rock quality index (Q): Among them, RQD is the rock quality index, which reflects the continuity and integrity of the drill core; UCS is the uniaxial compressive strength of rock, which indicates the strength of the rock itself; and Jn, Jr, and Jw in the e-index are adjustment coefficients for joint spacing, roughness, and groundwater conditions, which reflect the impact of these factors on the stability of the surrounding rock. The calculated Q value needs to be adjusted and calibrated according to the actual geological conditions and engineering experience to ensure that it accurately reflects the quality of the surrounding rock. Finally, the RMQI is calculated based on the adjusted Q value, combined with the ground stress and other relevant parameters. This index can comprehensively reflect the overall quality and stability of the surrounding rock, and provide an important decision-making basis for the design and construction of the tunnel. Generally, the higher the RMQI value, the more stable the surrounding rock, and vice versa, it indicates that the surrounding rock is less stable and additional support measures may be needed. The index is a dimensionless value from 0 to 100, where 0 indicates the lowest quality of the surrounding rock and 100 indicates the best quality of the surrounding rock. The system sets five level thresholds for RMQI: 80 and above for A (excellent), 60 to 79 for B (good), 40 to 59 for C (medium), 20 to 39 for D (poor), and below 20 for E (poor). When the RMQI is below 40, the system automatically rates the surrounding rock as D or E and triggers an alarm mechanism, prompting the construction team that reinforcement measures may be needed. The evaluation results are displayed in real time through an intuitive digital dashboard and graphical interface, allowing the construction team to quickly grasp the surrounding rock quality status. For example, if the RMQI calculation result is 55, the system will display "Surrounding rock quality grade: C (medium)" and provide further analysis reports and recommended support plans. This automated, numerical evaluation process not only improves the accuracy and efficiency of surrounding rock quality evaluation, but also provides real-time, scientific decision-making support for tunnel construction.

[0056] The adaptive support design optimization module is used to obtain the surrounding rock quality index and recommend the required support scheme according to the surrounding rock quality index.

[0057] The operation process of the adaptive support design optimization algorithm is as follows: The algorithm first receives real-time geological data and rock mass quality index (RMQI) from the intelligent surrounding rock quality evaluation system. The data update frequency is set to once every 10 seconds to ensure that the design parameters are synchronized with the latest geological conditions. The algorithm has a built-in parameter database that stores the support design schemes corresponding to different RMQI values. For example, when the RMQI is in the range of 80 to 100, the Class A support scheme is recommended, and the support strength required is 1.0MPa and the steel bar spacing is 150mm. Then, the algorithm uses a fuzzy logic controller to comprehensively evaluate the RMQI and other environmental parameters (such as groundwater level, ground stress, etc.). Other environmental parameters, such as groundwater level and ground stress, are usually obtained in the following stages: In the early stage of tunnel or engineering project planning, geological exploration is carried out to obtain a preliminary understanding of the geological conditions of the site, including the distribution of groundwater level and ground stress. This stage may include activities such as geological mapping, geophysical exploration, and drilling tests. Before construction begins, more detailed geological surveys and monitoring are carried out to obtain accurate groundwater level and ground stress data. This helps to design more reasonable support structures and construction methods. During the tunnel construction process, the changes in groundwater level and ground stress are continuously monitored. This is usually achieved by installing monitoring equipment in the tunnel, such as water level gauges, stress sensors, etc., to capture the dynamic changes of environmental parameters in real time. After the construction is completed, it may also be necessary to monitor these environmental parameters regularly to evaluate the long-term stability and safety of the structure. This is particularly important for tunnels during operation to prevent possible geological disasters. Determine the optimal support parameters under the current geological conditions. By arranging water level gauges along the tunnel, the groundwater level data is recorded regularly. These data reflect the changes in the pressure of groundwater on the tunnel surrounding rock. The ground stress is measured in front of and around the tunnel face using ground stress gauges. These data are crucial for evaluating the stability of the surrounding rock. Combined with the calculation of the rock quality index (RMQI), factors such as the uniaxial compressive strength, crack spacing, roughness and groundwater conditions of the rock are considered. For example, the formula is used: RMQI = 100 × e-(a × crack spacing + b × roughness + c × groundwater conditions); where a, b, and c are weight coefficients adjusted according to geological conditions. Take RMQI, groundwater level and ground stress as input variables. Define fuzzy sets for each input variable, such as "high", "medium" and "low". Formulate fuzzy rules based on expert experience and historical data. For example, if RMQI is "low" and groundwater level is "high", the surrounding rock stability is "poor". Use fuzzy logic controller to process input data, make inferences based on fuzzy rules, and output fuzzy values ​​of surrounding rock stability. Convert fuzzy output into clear numerical values ​​and use centroid method to calculate specific stability index. According to the defuzzified stability index, combined with engineering experience and design specifications, determine the optimal support parameters.For example, if the stability index is less than 3.5, it may be necessary to increase the thickness of the shotcrete, increase the density of the anchors, or use higher-strength steel supports. During the construction process, the changes in groundwater levels and ground stresses are monitored in real time to dynamically adjust the support design. For example, if a sudden rise in groundwater levels is detected, drainage measures may need to be added immediately. A feedback mechanism is established to adjust the parameters and rules of the fuzzy logic controller based on the actual performance and monitoring data during the construction process to improve the accuracy of the assessment. Project engineers and geological experts will make the final support decision based on the output of the fuzzy logic controller and combined with the site conditions. This may include changing the construction method, adjusting the support type, or adding additional monitoring measures.

[0058] For example, if the groundwater level suddenly rises and the surrounding rock stability decreases, the algorithm will automatically increase the support strength to 1.2MPa and adjust the spacing of the steel bars to a denser configuration. Subsequently, the algorithm uses a genetic algorithm to optimize the support design scheme to find the lowest cost support scheme while meeting safety requirements. The optimization process takes into account factors such as material cost, construction difficulty and expected service life to ensure the economy and sustainability of the design scheme. The support design parameters output by the algorithm include support type, support strength, steel bar diameter and spacing, etc. These parameters are transmitted to the construction management system in real time through a digital interface. The construction team quickly adjusts the construction plan and support measures based on the design scheme provided by the algorithm to ensure the safety and efficiency of the construction process. If the real-time geological data shows that the RMQI drops to 55, the algorithm will automatically adjust the support design and output "recommended support strength: 1.1MPa, steel bar diameter: 20mm, spacing: 200mm", and prompt the construction team to take corresponding measures. This automated design optimization process realizes the intelligence and personalization of support design, significantly improving the adaptability and safety of tunnel construction.

[0059] The intelligent construction equipment monitoring system is used to obtain operating parameters of construction equipment and to generate an alarm when the operating parameters exceed a first preset threshold.

[0060] The intelligent construction equipment monitoring system uses IoT sensors installed in key locations to accurately collect equipment operating parameters once per second, including temperature readings not exceeding 250°C, vibration frequencies not exceeding 50Hz, and pressure values ​​not exceeding 150 bar. If the temperature monitored in the intelligent construction equipment monitoring system exceeds 250°C, the vibration frequency exceeds 50Hz, or the pressure exceeds 150 bar, the system will immediately sound an alarm, record abnormal data, and may automatically stop the equipment from running to prevent damage. Subsequently, the maintenance team will intervene to diagnose the fault and make necessary repairs to ensure that the equipment will restart and continue its monitoring and data collection tasks only after the problem is solved. This design ensures safety and the health of the equipment during the construction process. These key locations include the engine and power system to monitor speed, temperature, and pressure; the hydraulic system to track pressure and flow; the electrical system to detect current and voltage; the mechanical transmission system to focus on vibration and noise; the working device to evaluate force and wear; the structural components to monitor stress and deformation; the control system to ensure the accuracy of the operation; the environmental monitoring device to ensure the safety and health of the operator; the positioning and navigation system to provide accurate location information of the equipment; and the safety device to ensure rapid response in an emergency. Through the data collected by these sensors, the intelligent monitoring system can analyze and predict potential failures in real time, realize preventive maintenance, and thus improve the efficiency and safety of construction. These data are transmitted to the central monitoring platform in real time via wireless network. The processing capacity of the platform ensures that the data can be analyzed within a delay of no more than 100 milliseconds. Using machine learning algorithms, such as random forest classifiers, the data is pattern recognized. If the torque sensor reading of a shield machine cutterhead is detected to suddenly rise to 120% of the predetermined threshold, the system will automatically mark it as abnormal and calculate its failure probability. If the failure probability exceeds 75%, the system will issue an early warning through the visual interface at least 10 hours before the predicted failure occurs, and send the early warning information to the maintenance team's mobile device through the automatic notification system. The information contains the type of failure, possible causes and specific maintenance measures, ensuring that the construction team can respond in time, carry out maintenance or repair in advance, and minimize the risk of construction interruption and equipment damage.

[0061] The environment monitoring module is used to obtain the environment parameters inside the tunnel and to generate an alarm when the environment parameters exceed a second preset threshold.

[0062] The operation process of the environmental monitoring module is specific and systematic: the module first collects environmental parameters in real time through multiple sensor nodes distributed inside the tunnel. These sensors are specially designed to accurately measure temperature (ranging from -20℃ to 50℃), relative humidity (0% to 100%) and gas concentrations, such as carbon monoxide (CO), methane (CH4) and other harmful gases (0 to 1000ppm). The data collection frequency is set to once every 5 seconds to ensure a rapid response to changes in the construction environment. The collected data is initially processed by the module's built-in microcontroller, including data calibration and outlier removal to ensure data accuracy. Subsequently, the processed data is transmitted to the central monitoring station via a wireless communication network at a rate of at least 10 megabits per second. At the central monitoring station, an environmental data analysis system further analyzes the collected data. The system uses statistical methods and trend prediction models to evaluate the stability and safety of the environment in the tunnel. If any of the monitored environmental parameters exceeds the preset safety threshold, such as temperature exceeding 40℃, humidity below 30%, or gas concentration exceeding the safety standard, the system will automatically trigger an alarm and notify construction management personnel and operators through sound and light signals and text messages. At the same time, the system will also initiate corresponding environmental control measures, such as starting the ventilation system to reduce temperature or increase humidity, to ensure that the construction environment quickly returns to a safe range. The environmental monitoring module also has data recording and historical trend analysis functions, which can provide the construction team with long-term trends and predictions of environmental changes and assist in the formulation and adjustment of construction plans. Through this continuous and automated environmental monitoring and control process, this embodiment ensures the safety of the tunnel construction environment and the smooth progress of construction operations.

[0063] The safety early warning system is used to: obtain safety monitoring parameters; the safety monitoring parameters include: operating parameters of the construction equipment and environmental parameters inside the tunnel; use pattern recognition methods to identify whether the safety monitoring parameters have potential safety risks based on a historical case database.

[0064] The operation process of the safety warning system is precise and automated: the system first integrates real-time monitoring data streams, including key parameters such as temperature, humidity, and gas concentration provided by the environmental monitoring module, and equipment operation status information provided by the intelligent construction equipment monitoring system. The data analysis engine inside the system processes this data once a minute, and conducts in-depth analysis of the data by applying machine learning algorithms such as support vector machines (SVM) and neural networks to identify abnormal patterns that may occur during the construction process. Abnormal pattern recognition in the intelligent construction equipment monitoring system is a multi-level data analysis process that predicts and identifies potential problems by analyzing a large amount of data from the construction site in real time. First, the system collects data from sensors installed at key locations, which may include parameters such as temperature, vibration frequency, and pressure of construction equipment. The data is pre-processed, such as denoising and normalization, to ensure its accuracy and usability. The system uses feature extraction technology to identify key information from the raw data, which can represent important variables and trends in the construction process. Then, by applying machine learning algorithms, the system conducts in-depth analysis of these features to distinguish between normal operating conditions and abnormal patterns. During this process, the system refers to a historical case database that contains data collected and recorded events from past projects to train and optimize the recognition model. Abnormal patterns may include adverse situations in various construction processes, such as equipment performance degradation, construction schedule delays, resource waste, safety hazards, or environmental impacts. These anomalies may appear as sudden changes in data, persistent deviations, or trends that do not meet expectations. For example, if the vibration frequency suddenly increases, it may indicate wear or damage inside the equipment. Once the system identifies a potential abnormal pattern, an alarm will be automatically triggered and a real-time notification will be sent to construction managers. In this way, managers can take quick action, such as adjusting construction plans, performing equipment maintenance, or strengthening safety measures to avoid potential risks and losses. The intelligent monitoring system has self-learning capabilities and can continuously optimize its anomaly detection capabilities based on newly collected data and historical cases. This continuous learning and optimization ensures that the system can adapt to changes in the construction process and improve the accuracy and efficiency of anomaly detection. The system also contains a historical case database that stores safety events and solutions in previous construction cases, providing the system with rich reference information. Combining real-time data and historical cases, the safety early warning system uses pattern recognition technology to predict potential safety risks such as structural instability, equipment failure, or environmental hazards. Once the system detects any abnormality or risk indicators, such as carbon monoxide concentration in the tunnel exceeding the safety threshold of 200ppm or surrounding rock displacement rate exceeding 2mm per day, it will automatically trigger the alarm mechanism. The alarm will sound an audible alarm through the public broadcasting system in the tunnel and send emergency notifications to construction managers and safety managers through the wireless communication network.In addition, the system will automatically initiate emergency plans, such as evacuating construction personnel, suspending construction work, or starting ventilation systems to reduce risks and protect personnel safety. The safety early warning system also includes a feedback mechanism that allows on-site construction personnel to confirm alarms and provide real-time feedback, based on which the system adjusts early warning strategies and emergency response measures. Through this process of continuous monitoring, intelligent analysis, and automatic response, the safety early warning system ensures high safety standards and rapid response capabilities during tunnel construction.

[0065] The construction data analysis and decision support system is used to: obtain data from the intelligent construction equipment monitoring system, environmental monitoring module and safety warning system to obtain safety data; obtain construction progress, material usage and worker activity data to obtain construction data; and use historical construction data in combination with the safety data and the construction data to predict construction trends.

[0066] The construction data analysis and decision support system plays a core role in this embodiment, and its workflow is as follows: The system first collects a large amount of data generated during the construction process in real time from multiple data sources such as the intelligent construction equipment monitoring system, environmental monitoring module, and safety early warning system, including equipment status, environmental parameters, safety events, etc. These data flow into the system at a rate of millions of records per second, and are cleaned, standardized, and integrated by the data preprocessing module to ensure data quality. The system uses big data analysis techniques, such as data mining and pattern recognition, to conduct in-depth analysis of the integrated data to identify key trends and potential problems in the construction process. Abnormal pattern recognition in the intelligent construction monitoring system is a meticulous and multi-level process that relies on accurate data collection and advanced analysis techniques. The system collects specific parameters in real time through sensors deployed at the construction site, such as the temperature reading of the equipment (not exceeding 250°C), vibration frequency (not exceeding 50Hz), and pressure value (not exceeding 150 bar). These parameters are key indicators for identifying whether the equipment is operating normally. The data preprocessing step ensures the accuracy and consistency of these raw data, by cleaning out noise and outliers and standardizing the data to prepare for further analysis. In the feature extraction phase, the system analyzes data such as construction progress, material usage, and worker activities to identify key trends in project operations. For example, if the temperature reading of the equipment continues to approach the upper limit of 250°C, the system will mark this trend and combine the data of vibration frequency and pressure values ​​to use machine learning algorithms for in-depth analysis to determine whether there is a problem of overheating or abnormal wear. The system's predictive modeling function uses historical construction data, combined with currently monitored parameters, to predict possible future problems such as equipment failure or construction delays. For example, if the temperature and vibration frequency are abnormal at the same time, the system will predict that the equipment may be about to fail and issue an alarm immediately. In this way, the maintenance team can take action before the problem occurs, conduct necessary inspections and repairs, and avoid potential downtime and safety risks. The intelligent construction monitoring system provides decision support for project managers through real-time alerts and visual reports. These reports not only include the current construction status, but may also contain predictions of future risks and recommended preventive measures. This data-based approach enables construction teams to proactively manage projects, optimize resource allocation, ensure construction safety, control costs, and reduce environmental impact. At the same time, artificial intelligence algorithms, including deep learning and natural language processing, intelligently analyze construction data, automatically extract features and build predictive models, and use Internet of Things (IoT) devices such as sensors and cameras to collect data such as temperature, humidity, equipment status and operating conditions at the construction site in real time. RFID tags and GPS technology are used to track the transportation and use of materials and equipment. Drones are used for regular on-site monitoring to collect image data to monitor construction progress. Outliers and noise are removed, for example, abnormal temperature readings caused by sensor failures are eliminated.Merge data from different sources (such as sensor data, operation logs, weather information) into a central database. Extract useful features from raw data, for example, extract daily concrete usage from operation logs. ARIMA model for predicting construction progress. This model analyzes historical construction data to identify periodic and trend components to predict future construction activities. LSTM network for predicting resource demand. LSTM network is able to learn long-term dependencies in time series data to predict the use of specific resources in the future. Ensemble learning method: Combine the prediction results of multiple models, such as random forest and gradient boosting machine (GBM), to improve the accuracy and robustness of predictions. Use historical construction data to train the model, such as data from similar projects completed in the past few years. Evaluate the performance of the model through cross-validation methods to ensure that the model maintains high prediction accuracy on different data sets. Construction progress prediction: Based on the prediction results of the ARIMA model, project managers can adjust the construction plan, such as increasing labor or extending working hours, to ensure that the project is completed on time. Based on the prediction results of the LSTM network, purchase necessary materials and equipment in advance to avoid construction delays caused by resource shortages. By analyzing the forecast results, potential risk points such as equipment failure or weather impact can be identified, and response strategies can be formulated in advance. Real-time monitoring of construction site data and dynamic update of the forecast model to reflect the latest construction conditions. When the actual construction progress deviates from the forecast results, the system automatically adjusts the forecast model to provide the latest forecast results. For example, time series analysis is used to predict construction progress and resource requirements. The system's built-in decision support engine provides scientific decision-making suggestions to the construction management team based on the analysis results, such as adjusting the construction plan, optimizing resource allocation, and preventing potential risks. These suggestions are presented in the form of visual reports and real-time notifications to ensure the timeliness and accuracy of construction decisions. The system also has self-learning capabilities, which can continuously optimize analysis models and decision-making suggestions based on feedback from the construction team and new construction data, thereby improving the system's forecast accuracy and the effectiveness of decision support. The self-learning ability of the intelligent construction monitoring system is mainly achieved through machine learning and artificial intelligence technologies. The specific process includes data-driven model training, online learning, model optimization, and continuous feedback. The following are the specific steps to obtain self-learning capabilities: The system collects a large amount of historical construction data and real-time monitoring data, which are used as training sets to train machine learning models. With supervised learning, the model learns patterns and relationships from labeled data, while unsupervised learning allows the model to discover hidden patterns in data that is not explicitly labeled. The system has the ability to learn online, which means it can update the model on the fly as new data arrives, without the need to retrain the entire dataset. This capability allows the system to adapt to changes in the construction process, capture new patterns, and improve the accuracy of predictions. Techniques such as cross-validation and grid search are used to optimize model parameters.The system continuously adjusts and tests different parameter combinations to find the best model configuration to improve prediction performance. The system adjusts the prediction model based on actual construction results and feedback. For example, if the actual construction progress is significantly different from the predicted progress, the system analyzes the reasons for the difference and updates the model to reduce future prediction errors. In some cases, the system may use reinforcement learning techniques to learn the optimal strategy through interaction with the environment. In construction monitoring, this means that the system adjusts its behavior based on the results of construction operations to achieve better construction management and resource allocation. The system may use transfer learning techniques, which allows the model to apply what it has learned in one project to another similar project. This is especially useful for new or uncommon construction scenarios because it allows the system to quickly adapt to new environments. The system integrates the prediction results of multiple models to improve the overall prediction performance through model fusion techniques such as stacking, boosting, or ensemble learning. The system can automatically discover and generate new features that may be more useful for the prediction model. For example, the system may identify the relationship between a specific combination of certain construction operations and resource consumption. Through this intelligent data analysis and decision support process, the construction data analysis and decision support system has significantly improved the efficiency of construction management and the intelligence level of the construction process.

[0067] The material supply chain management system is used to: obtain the inventory level and supply chain status of materials required in the construction project; use intelligent prediction algorithms to predict future material needs based on material consumption rates and inventory levels; generate purchase orders based on the future material needs and inventory levels, and send order information to suppliers through electronic data interchange technology.

[0068] The material supply chain management system plays a key role in ensuring the continuity and efficiency of construction in this embodiment. Its specific workflow is as follows: the system first connects to the supplier database through a real-time data interface to automatically track the inventory level and supply chain status of the materials required in the construction project. Using the preset threshold and intelligent prediction algorithm, the system analyzes the material consumption rate and inventory every two hours, predicts future material demand, and ensures the timely replenishment of materials. The system's built-in order management module automatically generates purchase orders based on the prediction results and safety inventory levels, and sends order information to suppliers through electronic data interchange (EDI) technology to achieve rapid response. At the same time, the system also monitors the logistics status, updates the transportation progress and expected arrival time of materials in real time, and ensures the accuracy of material supply. After the materials arrive at the construction site, the system uses RFID technology or barcode scanning to manage the warehousing of materials to ensure the accuracy and traceability of material information. In addition, the system also supports material inventory optimization, automatically adjusts inventory strategies according to the construction progress and material consumption patterns, reduces inventory costs, and improves material turnover. The system also includes a risk management module to evaluate potential risks in the supply chain, such as supplier delays, logistics interruptions, etc., and formulate corresponding response strategies. Through this comprehensive material supply chain management process, the system ensures the continuity, timeliness and accuracy of material supply during tunnel construction, thereby supporting the smooth progress of the construction project as planned.

[0069] The personnel positioning and management system is used to obtain the location information of each person and send an alarm to the person when the person approaches a dangerous area or exceeds a preset safety range.

[0070] The personnel positioning and management system plays a vital role in the present invention, and its workflow is as follows: First, the system equips each construction worker entering the tunnel with an RFID tag or other type of positioning device, which has a unique identity and can send a location signal at least once per second. Multiple readers are installed inside the tunnel, which are arranged in a predetermined grid to ensure coverage of the entire construction area to receive signals from the tags in real time. The core of the system is a central monitoring platform, which uses advanced positioning algorithms to process the received signals to determine the exact location of each tag with an accuracy of less than 1 meter. Once the positioning data is determined, the system will update the location information of the construction workers in real time and display the current location of each person on a three-dimensional map of the tunnel. The system also integrates a safety warning module. When the construction workers approach the dangerous area or exceed the preset safety range, the system will automatically send an alarm to the relevant personnel and notify the construction management personnel to take necessary safety measures. The system also has an emergency evacuation function. Once an emergency occurs in the tunnel, the system can quickly guide the personnel to evacuate to a safe area. In order to improve management efficiency, the system also provides personnel attendance and working time tracking functions, automatically recording the entry and exit time of personnel and working hours, and providing data support for project management and resource planning. Through this comprehensive personnel positioning and management system, this embodiment ensures the safety of tunnel construction workers and improves the efficiency and response speed of construction management.

[0071] The rock tunnel intelligent support system that is adaptive to geological conditions also includes: a digital twin technology application module.

[0072] The digital twin technology application module in this embodiment undertakes the key task of realizing accurate digital mapping of tunnel construction. Its specific workflow is as follows: First, the system collects physical data of the tunnel construction site through integrated three-dimensional scanning technology and high-precision sensors. These data include but are not limited to the size, shape and geological characteristics of the tunnel and the surrounding rock. Subsequently, advanced data processing software is used to convert the collected physical data into an accurate three-dimensional digital model, which truly reflects the actual situation of the tunnel at a 1:1 ratio. The system quickly extracts geological information from the generated three-dimensional digital model and automatically identifies the type, structure and potential geological defects of the surrounding rock by applying machine learning and pattern recognition technology. The system also supports visualization of geological information, and clearly displays the geological structure and possible risk points inside the tunnel through different colors and logos. In the digital twin module of the intelligent construction monitoring system, the geological structure and potential risk points inside the tunnel are displayed through carefully designed visual logos. The display of geological structure usually uses different colors to distinguish different types of rocks and geological features. For example, blue is used to represent hard granite, yellow is used to represent softer sandstone, and red may be used to mark broken zones or faults. As for the identification of risk points, specific symbols or patterns may be used, such as exclamation marks to indicate potential landslide areas and water drop patterns to indicate possible water seepage points. The data of these geological structures and risk points are obtained through high-precision geophysical detection devices such as 3D scanning technology, geological radar detection, seismic wave velocity measuring instruments and ground stress meters. These devices are arranged at certain intervals around the tunnel, collecting parameters such as density, humidity, and strength of the surrounding rock in real time, and transmitting the data to the central processing station. There, after preprocessing and analysis, the data is used to generate a 3D digital model of the tunnel. The model incorporates information on geological structures and risk points, providing the construction team with an intuitive basis for risk assessment and planning. The digital twin module also has a real-time update function, which can dynamically adjust the digital model according to new geological data and monitoring results during the construction process to ensure that the model always reflects the latest construction status. The system also supports integration with construction data analysis and decision support systems, using digital twin models as an intuitive basis for decision making. The application of digital twin models in construction decision-making is a comprehensive and multi-step process involving multiple stages such as data collection, model construction, analysis and prediction, and decision execution. First, by using high-precision 3D scanning technology, geological radar, seismic wave velocity measurement instruments and ground stress meters, detailed data on the tunnel and its surrounding geological environment are collected. These data include key geological parameters such as rock type, fracture distribution, groundwater level and ground stress. Then, these data are used to create a 3D digital model with a 1:1 scale of the actual tunnel. In this model, different colors and logos are used to distinguish various geological structures and risk points. For example, fracture zones may be marked in red, high stress areas may be represented in purple, and potential water seepage points are marked with water drop patterns.

[0073] Once a digital twin model is created, it can be used to simulate the construction process and predict possible problems. By simulating different construction options in the model, such as different excavation paths or support designs, the project team can evaluate the geological risks and construction difficulties of each option. For example, the model may predict that construction may encounter the risk of landslides due to rock fragmentation and high stress conditions in a certain area. In addition, the model can also be used to simulate environmental impacts, such as the impact of construction activities on groundwater level changes. Based on the analysis results of the digital twin model, project managers can make more informed decisions. For example, they may decide to take additional support measures in high-risk areas or adjust the construction path to avoid areas with the most complex geological conditions. In addition, the digital twin model can also assist in resource allocation decisions, helping project managers optimize the scheduling of materials and equipment by predicting resource requirements at different construction stages. During the construction process, the digital twin model can also be updated based on real-time monitoring data to reflect the latest geological conditions and construction progress, ensuring that decisions are always based on the most accurate information. The digital twin model not only plays a role before and during construction, but also can be used for decision support in the operation and maintenance stages after the construction is completed. For example, by analyzing the long-term geological stability data in the model, managers can develop preventive maintenance plans to extend the service life of the tunnel. At the same time, the digital twin model can also be used as a communication and training tool to help project team members better understand geological conditions and construction plans, and improve the overall collaboration efficiency of the team. Assist the construction team to conduct more accurate risk assessment and construction planning. The digital twin technology application module provides a highly realistic and interactive virtual environment for tunnel construction, allowing the construction team to perform plan previews, risk analysis and decision-making in a virtual space, greatly improving the safety and efficiency of construction.

[0074] The rock tunnel intelligent support system that is adaptive to geological conditions also includes: a machine vision and intelligent recognition technology module.

[0075] The machine vision and intelligent recognition technology module plays a key role in automatically identifying surrounding rock features and intelligent grading in this embodiment. Its specific workflow is as follows: The system first deploys high-definition camera equipment on the tunnel construction surface to capture image data of the surrounding rock surface in real time. These images are transmitted to the central processing unit at a rate of at least 30 frames per second through the image acquisition module to ensure the continuity and real-time nature of the image data. In the central processing unit, the image preprocessing algorithm first performs denoising, contrast enhancement and edge detection on the received images to improve the recognizability of geological features in the image. Subsequently, a deep learning convolutional neural network (CNN) is applied to perform feature extraction and pattern recognition on the image to automatically identify cracks, joints and other surrounding rock features in the image. The system's built-in intelligent grading algorithm intelligently grades the surrounding rock based on the identified features and combines geomechanical parameters to collect key geological data, including the uniaxial compressive strength, elastic modulus, crack spacing, roughness and groundwater conditions of the rock. These data are obtained through high-precision geological exploration equipment and field monitoring instruments, providing a scientific basis for surrounding rock grading. An intelligent grading model is developed using machine learning or deep learning algorithms combined with expert systems. This model can automatically and objectively classify the surrounding rock based on the input geomechanical parameters. Usually, the surrounding rock classification is divided into five levels: Level I indicates that the rock is intact and strong, suitable for rapid construction; Level II indicates that the rock is relatively intact and requires certain support measures; Level III indicates that the rock is moderately broken and requires moderate support; Level IV indicates that the rock is severely broken and requires a lot of support and reinforcement measures; and Level V indicates that the rock is extremely broken and has extremely poor stability, requiring special treatment and enhanced support. The basis for classification mainly includes the strength, integrity, ground stress state, groundwater conditions and historical geological events of the rock. For example, high uniaxial compressive strength and low crack spacing usually indicate that the rock is strong and intact, so it is classified as a higher grade. On the contrary, low strength and high crack spacing may mean that the rock is poorly stable and requires more support measures. The classification results reflect the stability of the surrounding rock and the support measures that may be required. For example, the system may classify the surrounding rock into five grades, from Grade I (excellent) to Grade V (extremely poor), and automatically recommend the corresponding construction plan and support design. Specifically, detailed data about the tunnel surrounding rock is collected from geological exploration and field monitoring equipment, including parameters such as the uniaxial compressive strength, elastic modulus, crack density, roughness, groundwater level and ground stress of the rock. These data are transmitted to the central processing unit in real time and preprocessed to ensure the accuracy and availability of the data. Using machine learning algorithms, combined with geomechanical parameters and historical construction data, the system automatically classifies the surrounding rock. For example, based on the strength and crack density of the rock, the surrounding rock may be divided into Grade I (excellent) to Grade V (extremely poor). The system has a built-in construction plan database, which contains recommended construction methods and support designs for different surrounding rock grades and geological conditions.According to the surrounding rock classification results, the system automatically queries the database to match the most suitable construction plan. In addition, the system will consider the environmental changes monitored in real time, such as the sudden rise of groundwater level or the increase of ground stress, to further optimize the recommended plan. When recommending a plan, the system will evaluate the safety and economy of the plan at the same time. The safety assessment considers whether the plan can ensure the safety of construction personnel and the stability of the tunnel, while the economic assessment considers the cost-effectiveness of the plan to ensure that the construction cost is controlled while meeting safety requirements. The recommended construction plan and support design will be presented to the construction team through an intuitive user interface. These plans include detailed technical parameters, construction steps, required material specifications and expected construction time. Based on this information, the construction team can make decisions quickly and adjust the construction plan. During the construction process, the system will continuously monitor the changes in geological conditions and dynamically adjust the recommended plan based on the new data. For example, if a sudden increase in ground stress is detected, the system may recommend increasing the support strength or changing the support design to ensure construction safety. The system also has the ability to self-learn and optimize, and can continuously adjust the recognition algorithm and classification standards based on the feedback provided by the construction personnel and new geological data to improve the accuracy of recognition and the scientific nature of classification. Through this automated machine vision and intelligent recognition process, the present invention significantly improves the efficiency and accuracy of surrounding rock assessment during tunnel construction.

[0076] The rock tunnel intelligent support system that is adaptive to geological conditions also includes: an integrated control system, which is used to coordinate and control information sharing and collaborative work among various modules.

[0077] As the core hub of this embodiment, the integrated control system is responsible for realizing data integration, intelligent decision-making and rapid response among various submodules. Specifically, the system first collects data streams from intelligent advanced geological prediction, surrounding rock quality evaluation, construction equipment monitoring, environmental monitoring, safety warning, construction data analysis, material supply chain management, personnel positioning management, digital twin technology, and machine vision and intelligent recognition modules in real time through a central data bus. Using efficient data fusion technology, the integrated control system integrates these heterogeneous data sources to form a unified construction data view. The system's built-in intelligent decision-making engine uses advanced optimization algorithms and artificial intelligence technologies to conduct in-depth analysis of integrated data and generate the optimal decision-making plan during the construction process. For example, according to the results of geological prediction and surrounding rock evaluation, support parameters are intelligently adjusted; according to environmental and safety monitoring data, potential risks are warned in real time and emergency response is triggered. The integrated control system also has a strong real-time response capability, and can quickly implement decision results through automated actuators such as automatic valves, robotic arms and robots according to the instructions of the intelligent decision-making engine. For example, when the safety warning system issues an alarm, the integrated control system can quickly mobilize emergency resources, guide personnel to evacuate, and adjust construction equipment and environmental control systems to ensure construction safety. The system also includes a user interface that graphically displays the construction status and decision results, making it easier for construction managers to monitor and operate. Through the coordination of the integrated control system, a high degree of information sharing and collaborative work is achieved between the modules, ensuring the intelligent, automated and efficient management of the entire tunnel construction process.

[0078] In an exemplary embodiment, Figure 2 As shown, a rock tunnel intelligent support method that is adaptive to geological conditions is provided, and the method includes:

[0079] Acquire tunnel face geological data, and use a deep learning network to predict the probability and risk level of geological changes based on the tunnel face geological data;

[0080] Acquiring surrounding rock data at the tunnel perimeter, and calculating a surrounding rock quality index based on the surrounding rock data;

[0081] Obtaining the surrounding rock quality index, and recommending a required support scheme according to the surrounding rock quality index;

[0082] Acquiring operating parameters of the construction equipment, and providing an alarm when the operating parameters exceed a first preset threshold;

[0083] Acquiring environmental parameters inside the tunnel, and issuing an alarm when the environmental parameters exceed a second preset threshold;

[0084] Acquiring safety monitoring parameters; the safety monitoring parameters include: operating parameters of the construction equipment and environmental parameters inside the tunnel;

[0085] Using pattern recognition methods to identify whether the safety monitoring parameters have potential safety risks based on a historical case database;

[0086] Obtain data from the intelligent construction equipment monitoring system, environmental monitoring module and safety early warning system to obtain safety data;

[0087] Obtain construction progress, material usage and worker activity data to obtain construction data;

[0088] predicting construction trends using historical construction data in combination with the safety data and the construction data;

[0089] Obtain inventory levels and supply chain status of materials needed for construction projects;

[0090] Use intelligent forecasting algorithms to predict future material needs based on material consumption rates and inventory levels;

[0091] Generate a purchase order based on the future material demand and the inventory level, and send the order information to the supplier through electronic data interchange technology;

[0092] The location information of each person is obtained, and an alarm is sent to the person when the person approaches a dangerous area or exceeds a preset safety range.

[0093] Specifically, the rock tunnel intelligent support method for adaptive geological conditions provided by this embodiment can also be described as follows:

[0094] S1. Intelligent advanced geological forecast: Start the intelligent advanced geological forecast module, use geophysical detection technology to collect geological data in front of the tunnel face in real time, analyze the data through deep learning algorithms, predict possible geological changes and potential risks, and update the geological forecast information every 5 seconds.

[0095] S2. Surrounding rock quality evaluation: The intelligent surrounding rock quality evaluation system automatically collects geological data including rock stress, wave velocity, etc., conducts comprehensive analysis through data fusion technology, automatically evaluates the surrounding rock quality every 10 seconds, and adjusts the support parameters according to the evaluation results.

[0096] S3. Support design optimization: The adaptive support design optimization algorithm dynamically adjusts the support structure design, such as support strength and reinforcement arrangement, based on real-time geological data and surrounding rock quality evaluation to ensure the optimal support solution, and updates the design parameters every minute.

[0097] S4. Construction equipment monitoring: The intelligent construction equipment monitoring system uses IoT sensors to monitor the operating status of construction equipment in real time, predicts potential failures through big data analysis, conducts status assessment every 15 seconds, and provides timely warnings.

[0098] S5. Environmental status monitoring: The environmental monitoring module monitors the temperature, humidity and gas concentration in the tunnel, collecting data every 5 seconds to ensure the safety of the construction environment.

[0099] S6. Safety risk warning: The safety warning system combines real-time monitoring data and historical cases to predict potential safety risks, such as gas accumulation or surrounding rock instability, and immediately triggers an alarm once a risk is detected.

[0100] S7. Construction decision support: The construction data analysis and decision support system analyzes construction data and provides decision suggestions, such as construction plan adjustment and resource allocation, and provides a decision support report every 30 minutes.

[0101] S8.Material supply monitoring: The material supply chain management system monitors material inventory and supply status, and updates material demand forecasts every 2 hours to ensure timely material supply.

[0102] S9. Personnel safety management: The personnel positioning and management system uses RFID technology to locate the position of personnel in the tunnel in real time, and updates the location information every 10 seconds to ensure personnel safety.

[0103] S10. Digital twin technology application: The digital twin technology application module creates a three-dimensional digital model of tunnel construction, updates geological information in real time, and provides digital mapping of the construction process.

[0104] S11. Machine vision and intelligent identification: The machine vision and intelligent identification technology module automatically identifies surrounding rock features, such as cracks and joints, through high-definition camera equipment, and performs intelligent classification, completing identification every 20 seconds.

[0105] S12. Integrated control: The integrated control system integrates the data and functions of all the above modules to perform data integration, intelligent decision-making and rapid response, such as automatically adjusting the construction process and resource allocation to ensure intelligent management of the entire tunnel construction process.

[0106] Through this series of specific and coordinated steps, this method achieves adaptive management of various geological and construction conditions during rock tunnel construction, improving construction safety and efficiency.

[0107] Through the system and method of the present invention, tunnel construction can achieve intelligent management under various geological conditions, improve the level of construction automation, reduce safety risks, and improve construction efficiency and quality.

[0108] In an exemplary embodiment, a rock tunnel intelligent support system with adaptive geological conditions is provided, including: an intelligent advanced geological prediction module, an intelligent surrounding rock quality evaluation system, an adaptive support design optimization algorithm, an intelligent construction equipment monitoring system, an environmental monitoring module, a safety early warning system, a construction data analysis and decision support system, a material supply chain management system, a personnel positioning and management system, a digital twin technology application module, a machine vision and intelligent recognition technology module, and an integrated control system. The intelligent advanced geological prediction module uses geophysical detection and deep learning technology to collect and analyze geological data to provide the system with early warning of geological risks; the intelligent surrounding rock quality evaluation system automatically completes real-time evaluation of surrounding rock quality based on the data of the advanced geological prediction and combined with the multi-source data collected by itself; the adaptive support design optimization algorithm receives the geological prediction and surrounding rock evaluation results and dynamically adjusts the support design. The system can realize real-time geological analysis and intelligent identification of surrounding rocks, and can also realize the digital mapping of the construction process.

[0109] The intelligent advanced geological prediction module includes a geophysical detection device for collecting geological data and a deep learning network for processing data and making predictions. The intelligent surrounding rock quality evaluation system includes a sensor array for collecting geological data and an intelligent algorithm for comprehensively analyzing geological data and automatically evaluating the quality of surrounding rocks. The adaptive support design optimization algorithm includes an interface for receiving geological and surrounding rock quality data in real time and an optimization engine for dynamically adjusting the support design scheme based on the data. The intelligent construction equipment monitoring system includes a sensor network for monitoring the status of construction machinery and an intelligent diagnosis system for analyzing status data and predicting equipment failures. The environmental monitoring module includes a sensor group for detecting environmental parameters in the tunnel and monitoring software for real-time feedback of environmental status. The safety warning system includes an expert system for analyzing construction risks and a response mechanism for automatically triggering an alarm when an abnormality is detected. The construction data analysis and decision support system includes a data warehouse for storing and processing construction data and an analysis tool for providing decision-making suggestions. The material supply chain management system includes a logistics tracking system for tracking the flow of materials and an intelligent prediction algorithm for predicting material demand.

[0110] The intelligent advanced geological prediction module deploys a series of high-precision geophysical detection devices, which are configured at predetermined locations on the tunnel face to collect key geological parameters such as geological structure, rock mechanical properties, and groundwater distribution in real time. Subsequently, the collected raw data is sent to the central processing unit through a secure data transmission network. In the central processing unit, the deep learning algorithm preprocesses the data, including data cleaning, standardization, and feature extraction, to enhance the accuracy and reliability of the signal. Next, the preprocessed data is input into a well-trained deep neural network model, which performs pattern recognition and risk assessment based on the characteristics of the geological data and combines the historical geological event database to predict the geological changes and potential risks that may be encountered ahead of the tunnel construction. Finally, the forecast results generated by the module are intuitively displayed through the user interface, and the construction team is notified in the form of real-time alerts to ensure that appropriate preventive measures are taken before the geological conditions change adversely.

[0111] The intelligent surrounding rock quality evaluation system starts a multi-source data acquisition unit, which is equipped with high-precision geological radar, seismic wave velocity measuring instrument, ground stress meter and groundwater level monitor. These devices are arranged around the tunnel at intervals of 0.5 meters to collect parameters such as density, humidity, strength, elastic modulus, ground stress state and groundwater level of the surrounding rock in real time. The data acquisition frequency is set to once every 10 seconds. Subsequently, the collected raw data is transmitted to the central processing station at a rate of 1 gigabit per second through the optical fiber communication network. In the central processing station, the data first passes through the pre-processing module for filtering, denoising and normalization to ensure data quality. Then, the data fusion processing unit uses fuzzy comprehensive evaluation method and neural network algorithm to conduct a comprehensive analysis of multi-source data. The algorithm takes into account the correlation and weight of geological data, and calculates the surrounding rock quality index (Rock Mass Quality Index, RMQI), which ranges from 0 to 100, where 0 indicates extremely poor surrounding rock quality and 100 indicates extremely good surrounding rock quality. The system automatically divides the surrounding rock into five grades, from A (excellent) to E (poor), based on the RMQI value, and updates the surrounding rock quality evaluation results in real time. Finally, the evaluation results are displayed through a visual interface, and when the RMQI value is lower than the preset threshold of 40, the system automatically issues an alarm to prompt the construction team to take corresponding reinforcement measures.

[0112] After receiving the real-time geological data and rock mass quality index (RMQI) provided by the intelligent surrounding rock quality evaluation system, the adaptive support design optimization algorithm starts the dynamic design adjustment process at a frequency of every 10 seconds. The algorithm accesses the built-in parameter database and automatically selects the Class A support scheme according to the specific value of RMQI, such as when the RMQI is 80 to 100, and recommends a support strength of 1.0MPa and a steel bar spacing of 150mm. Using the fuzzy logic controller, the algorithm comprehensively evaluates the RMQI and other environmental parameters. If the groundwater level rises and the stability decreases, the algorithm will increase the support strength to 1.2MPa and adjust the steel bar spacing to enhance the support. Through further optimization by genetic algorithms, the algorithm outputs a set of economical and safe support design parameters considering cost, construction difficulty and durability. Finally, the construction team quickly implemented the adjustment of support measures based on the precise design scheme provided by the algorithm, such as "recommended support strength: 1.1MPa, steel bar diameter: 20mm, spacing: 200mm".

[0113] The intelligent construction equipment monitoring system collects key operating parameters of construction equipment, such as temperature, vibration and pressure, in real time through a series of precision IoT sensors, and updates the data once a second to ensure continuous monitoring of the equipment status. These data are transmitted to the central monitoring platform in real time via a high-speed wireless network at a rate of at least 10 megabits per second. On the platform, the big data mining analyzer uses machine learning algorithms, such as random forest classifiers, to conduct in-depth analysis of data streams to identify abnormal patterns in equipment behavior. For example, if the data of the cutter head torque sensor of a shield machine shows an abnormal increase, the analyzer will quickly evaluate this deviation, predict possible failures and issue an early warning 10 hours in advance. The early warning information is promptly communicated to the maintenance team through a visual interface and automatic notification system, providing detailed guidance such as the type of failure, cause and recommended maintenance measures, so that the construction team can quickly take preventive or repair measures, thereby improving the reliability and construction efficiency of construction equipment and reducing unexpected downtime.

[0114] The environmental monitoring module accurately collects environmental parameters such as temperature, humidity and gas concentration every 5 seconds through a sensor network evenly distributed in the tunnel. These sensors can cover a temperature range from -20°C to 50°C, monitor relative humidity from 0% to 100%, and harmful gas concentrations from 0 to 1000ppm. The data is transmitted to the central monitoring station and updated in real time at a rate of no less than 10 megabits per second through a wireless communication network. At the monitoring station, the environmental data analysis system uses statistical analysis and trend prediction models to evaluate the data to ensure environmental stability and safety. Once the parameters exceed the preset safety threshold, such as the temperature reaches 40°C or the gas concentration exceeds 500ppm, the system will immediately trigger an audible and visual alarm and notify the construction management personnel and operators through the SMS system. At the same time, environmental control measures are automatically initiated, such as increasing ventilation to reduce temperature or increase humidity, to quickly restore safe environmental standards. The environmental monitoring module also has long-term data recording and trend analysis functions to support construction plans and ensure that the construction environment is continuously in a safe state.

[0115] The safety warning system uses machine learning algorithms, such as support vector machines (SVM) and neural networks, to conduct in-depth analysis every minute to identify abnormal patterns in construction by integrating the data stream of the environmental monitoring module and the intelligent construction equipment monitoring system in real time. Combined with the historical case database, the system uses pattern recognition technology to predict potential safety risks. When an abnormality is detected, such as carbon monoxide concentration exceeding 200ppm or surrounding rock displacement rate exceeding 2mm / day, the system automatically triggers an alarm, issues an emergency notification through the tunnel broadcast and wireless network, and initiates emergency plans, such as evacuating personnel or enhancing ventilation. The system also includes a feedback mechanism that allows on-site personnel to provide real-time feedback so that the system can adjust the warning strategy.

[0116] The construction data analysis and decision support system collects massive construction data from multiple data sources such as intelligent construction equipment monitoring systems, environmental monitoring modules, and safety early warning systems in real time, and performs data preprocessing with the ability to process millions of records per second to ensure data accuracy. Using big data technology and artificial intelligence algorithms, including deep learning and natural language processing, the system conducts in-depth analysis of data, identifies key trends, and builds predictive models, such as time series analysis, to predict construction progress and resource requirements. The built-in decision support engine provides visual reports and real-time notifications to the construction management team, and recommends scientific construction plan adjustments and resource optimization strategies. The system also has self-learning capabilities, continuously optimizing models based on team feedback and new data to improve the accuracy of predictions and recommendations, thereby improving construction management efficiency and intelligence.

[0117] The material supply chain management system is connected to the supplier database through a real-time data interface, automatically analyzing and predicting the material demand and inventory levels of the tunnel construction project every two hours to ensure timely replenishment. The built-in order management module automatically generates purchase orders based on the analysis results and quickly places orders to suppliers through EDI technology. The logistics status is monitored in real time to update the transportation and estimated arrival time of materials. After the materials arrive, the system uses RFID or barcode technology for precise warehousing management, while supporting inventory optimization, automatically adjusting inventory strategies based on actual consumption patterns, reducing costs and improving efficiency. The risk management module evaluates potential supply chain risks and develops response strategies to ensure the continuous and accurate supply of materials in the construction project and support the project to proceed as planned.

[0118] The personnel positioning and management system equips each construction worker with an RFID tag or other positioning device to achieve real-time tracking of the location of personnel in the tunnel. These devices send signals at least once a second and are received by multiple readers in a preset grid layout in the tunnel. The central monitoring platform uses advanced positioning algorithms to process these signals, determine and update the location of each person on the three-dimensional map with an accuracy of within 1 meter in real time. The safety warning module automatically issues an alarm when personnel approach a dangerous area and guides evacuation to a safe area in an emergency. The system also includes personnel attendance and work time tracking functions, which automatically record and provide the data required for project management, thereby ensuring the safety of construction personnel and improving construction management efficiency and response speed.

[0119] The digital twin technology application module collects physical data from the tunnel construction site through 3D scanning and high-precision sensors, and converts this data into an accurate 3D digital model with a 1:1 ratio to the actual tunnel. The module uses machine learning technology to automatically identify and extract geological information from the model, such as surrounding rock type and structure, while providing a visual display that highlights geological structures and risk areas with different colors and logos. The module with real-time update capabilities can dynamically adjust the model based on the latest geological data and monitoring results to ensure that it reflects the current construction status. In addition, the module is integrated with the decision support system to provide the construction team with an intuitive risk assessment and planning basis, so that construction plan previews and decision-making can be carried out efficiently in a virtual environment, thereby improving construction safety and efficiency.

[0120] The machine vision and intelligent recognition technology module uses high-definition cameras to capture images of the tunnel construction surface and transmits them to the processing unit in real time at a rate of 30 frames per second. In this unit, the image is pre-processed by denoising, contrast enhancement and edge detection, and then the deep learning convolutional neural network performs feature extraction and pattern recognition to automatically identify surrounding rock features such as cracks and joints. The intelligent grading algorithm intelligently grades the surrounding rock based on these features and geomechanical parameters, such as from Grade I excellent to Grade V extremely poor, and recommends corresponding construction and support plans. The system also has a self-learning function, which continuously optimizes the algorithm based on feedback and new data to improve the accuracy of recognition and grading, thereby improving the efficiency and scientificity of construction evaluation.

[0121] The integrated control system serves as the central hub of the present invention. It integrates data streams from each submodule in real time through the central data bus, and uses data fusion technology to form a unified construction data view. The built-in intelligent decision-making engine uses optimization algorithms and artificial intelligence to deeply analyze the integrated data, generate and execute the optimal construction decision plan. For example, the support strategy is automatically adjusted according to the real-time geological and surrounding rock evaluation data, or the risk is warned in real time and emergency measures are triggered based on the environmental and safety monitoring data. The integrated control system also has the ability to respond quickly, and can quickly implement decisions through automated actuators, such as quickly deploying emergency resources and guiding personnel evacuation in case of safety warnings. The user interaction interface displays the construction status in a graphical form, which is convenient for monitoring and operation, ensuring the intelligent, automated and efficient management of the construction process.

[0122] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0123] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. An intelligent rock tunnel support system that is adaptive to geological conditions, characterized in that: The rock tunnel intelligent support system for adaptive geological conditions includes: an intelligent advanced geological prediction module, an intelligent surrounding rock quality evaluation system, an adaptive support design optimization module, an intelligent construction equipment monitoring system, an environmental monitoring module, a safety early warning system, a construction data analysis and decision support system, a material supply chain management module, a personnel positioning and management system and an integrated control system; The intelligent advanced geological prediction module is used to: obtain the geological data of the tunnel face, and use the deep learning network to predict the probability and risk level of geological changes based on the geological data of the tunnel face; The intelligent surrounding rock quality evaluation system is used to: obtain surrounding rock data at the tunnel perimeter and calculate the surrounding rock quality index based on the surrounding rock data; The adaptive support design optimization module is used to: obtain the surrounding rock quality index and recommend the required support scheme according to the surrounding rock quality index; The intelligent construction equipment monitoring system is used to: obtain the operating parameters of the construction equipment and issue an alarm when the operating parameters exceed a first preset threshold; The environmental monitoring module is used to: obtain environmental parameters inside the tunnel and issue an alarm when the environmental parameters exceed a second preset threshold; The safety warning system is used to: Acquiring safety monitoring parameters; the safety monitoring parameters include: operating parameters of the construction equipment and environmental parameters inside the tunnel; Using pattern recognition methods to identify whether the safety monitoring parameters have potential safety risks based on a historical case database; The construction data analysis and decision support system is used for: Obtain data from the intelligent construction equipment monitoring system, environmental monitoring module and safety early warning system to obtain safety data; Obtain construction progress, material usage and worker activity data to obtain construction data; predicting construction trends using historical construction data in combination with the safety data and the construction data; The material supply chain management system is used for: Obtain inventory levels and supply chain status of materials needed for construction projects; Use intelligent forecasting algorithms to predict future material needs based on material consumption rates and inventory levels; Generate a purchase order based on the future material demand and the inventory level, and send the order information to the supplier through electronic data interchange technology; The personnel positioning and management system is used to: obtain the location information of each person and send an alarm to the person when the person approaches a dangerous area or exceeds a preset safety range; The integrated control system is used to coordinate and control the information sharing and collaborative work among the modules.

2. The rock tunnel intelligent support system according to claim 1 is characterized in that: The rock tunnel intelligent support system that is adaptive to geological conditions also includes: a digital twin technology application module; The digital twin technology application module is used to: Obtain the size, shape and geological characteristics of the tunnel and surrounding rock to obtain physical data; constructing a three-dimensional digital model using the physical data; Using machine learning and pattern recognition methods to identify the type, structure and potential geological defects of the surrounding rock based on the three-dimensional digital model to obtain geological information; The geological information is visualized, and the geological structure and risk points inside the tunnel are displayed in the three-dimensional digital model through different colors and logos.

3. The rock tunnel intelligent support system according to claim 1 is characterized in that: The rock tunnel intelligent support system that is adaptive to geological conditions also includes: a machine vision and intelligent recognition technology module; The machine vision and intelligent recognition technology module is used for: Acquire image data of surrounding rock surface; Using a convolutional neural network to perform feature extraction and pattern recognition on the image data to obtain image features; the image features include: crack and joint features in the image data; Using an intelligent classification algorithm to intelligently classify the surrounding rock based on the image features and in combination with geomechanical parameters, a classification result is obtained; According to the classification results, corresponding construction plans and support designs are recommended.

4. The rock tunnel intelligent support system according to claim 1 is characterized in that: The intelligent advanced geological prediction module is specifically used for: Acquiring tunnel face geological data at a frequency of once per second; the tunnel face geological data is data within a preset range in front of the tunnel face; the tunnel face geological data includes rock stress, wave velocity and electromagnetic characteristics; Extracting geological parameter characteristics of the tunnel face geological data using a convolutional neural network; The geological parameter characteristics include: rock physical property characteristics, geological structure characteristics and groundwater distribution characteristics; The geological parameter characteristics are input into a trained deep learning network model to obtain the probability and risk level of geological changes at the corresponding position of the tunnel face geological data; the deep learning network model is trained by a historical geological event library; the geological changes include: rock fracture, landslide, rock burst, groundwater surge and fault activity.

5. The rock tunnel intelligent support system according to claim 1, characterized in that: The intelligent surrounding rock quality evaluation system is specifically used for: Acquire surrounding rock data at the tunnel perimeter; the surrounding rock data includes: density, moisture and compressive strength of the surrounding rock; Calculating a surrounding rock quality index based on the surrounding rock data; When the surrounding rock quality index is lower than a preset value, an alarm mechanism is triggered.

6. The rock tunnel intelligent support system according to claim 1, characterized in that: The personnel positioning and management system is specifically used for: Get the location information of each person; Processing the position information of each person using a positioning algorithm and displaying the current position of each person on a three-dimensional map of the tunnel; When a person approaches a dangerous area or exceeds a preset safety range, an alarm is sent to the person; When an emergency occurs in the tunnel, personnel are guided to evacuate to a safe area based on the location information. Record the entry and exit times and working hours of personnel, and transmit the entry and exit times and working hours to the construction data analysis and decision support system to provide data support for project management and resource planning.

7. The rock tunnel intelligent support system according to claim 1, characterized in that: The material supply chain management system is also used for: Monitor and update the transportation progress and estimated arrival time of materials in real time, and manage the entry of materials by using RFID technology or barcode scanning after the materials arrive at the construction site; Adjust inventory strategies based on construction progress and material consumption patterns; Use the risk management module to assess potential risks in the supply chain; The potential risks described include: supplier delays and logistics disruptions.

8. The rock tunnel intelligent support system according to claim 1, characterized in that: The intelligent construction equipment monitoring system is specifically used for: Obtaining operating parameters of construction equipment; the operating parameters include: speed, temperature and pressure of the engine and power system; pressure and flow of the hydraulic system; detection current and voltage of the electrical system; vibration and noise of the mechanical transmission system; When the operating parameter exceeds a first preset threshold, an alarm is given.

9. The rock tunnel intelligent support system according to claim 1, characterized in that: The environmental monitoring module is specifically used for: Acquiring environmental parameters inside the tunnel; the environmental parameters include temperature, relative humidity and gas concentration; the environmental parameters are collected by a number of sensors distributed inside the tunnel; When the temperature exceeds 40°C, the relative humidity is lower than 30%, or the gas concentration exceeds the safety standard, an alarm will be sounded and environmental control measures will be initiated.

10. An intelligent rock tunnel support method that is adaptive to geological conditions, characterized in that: The rock tunnel intelligent support method adapted to geological conditions comprises: Acquire tunnel face geological data, and use a deep learning network to predict the probability and risk level of geological changes based on the tunnel face geological data; Acquiring surrounding rock data at the tunnel perimeter, and calculating a surrounding rock quality index based on the surrounding rock data; Obtaining the surrounding rock quality index, and recommending a required support scheme according to the surrounding rock quality index; Acquiring operating parameters of the construction equipment, and providing an alarm when the operating parameters exceed a first preset threshold; Acquiring environmental parameters inside the tunnel, and issuing an alarm when the environmental parameters exceed a second preset threshold; Acquiring safety monitoring parameters; the safety monitoring parameters include: operating parameters of the construction equipment and environmental parameters inside the tunnel; Using pattern recognition methods to identify whether the safety monitoring parameters have potential safety risks based on a historical case database; Obtain data from the intelligent construction equipment monitoring system, environmental monitoring module and safety early warning system to obtain safety data; Obtain construction progress, material usage and worker activity data to obtain construction data; predicting construction trends using historical construction data in combination with the safety data and the construction data; Obtain inventory levels and supply chain status of materials needed for construction projects; Use intelligent forecasting algorithms to predict future material needs based on material consumption rates and inventory levels; Generate a purchase order based on the future material demand and the inventory level, and send the order information to the supplier through electronic data interchange technology; The location information of each person is obtained, and an alarm is sent to the person when the person approaches a dangerous area or exceeds a preset safety range.

Images