Rapid forming construction method based on high slope framed bent-free mechanization

Abstract

The invention relates to a rapid forming construction method based on high slope framed bent-free mechanization. The rapid forming construction method comprises the following steps that firstly, high-precision slope holographic digital modeling and intelligent planning are conducted; slope three-dimensional point cloud data are obtained through unmanned aerial vehicle laser scanning and oblique photography, a high-precision three-dimensional geologic model is constructed in combination with geological exploration data, multi-source data are fused to form a digital twinborn body, and an artificial intelligence algorithm is utilized to optimize blasting parameters, a robot operation path, material conveying scheduling and a layered and partitioned construction strategy; according to the method, through high-precision slope digital modeling and intelligent construction planning, blasting parameters, robot operation paths, material conveying and layered construction strategies are optimized in combination with an artificial intelligence algorithm, tight cooperation and conflict-free operation of construction links are achieved, different schemes can be simulated before construction, slope vibration and operation efficiency can be predicted, and the construction efficiency can be improved. Therefore, the construction period is shortened, resource waste is reduced, and construction continuity and overall efficiency are remarkably improved.

Description

Technical Field

[0001] This application relates to the field of water conservancy and hydropower construction technology, and in particular to a rapid prototyping construction method based on high slope without scaffolding and mechanization. Background Technology

[0002] High slope engineering is increasingly used in infrastructure construction such as water conservancy and hydropower, highways, and railways, and its stability is directly related to the safety and operation of the project. Traditional high slope support construction often uses scaffolding, but this method has problems such as long construction period, large material consumption, high safety risks, and high labor intensity. To solve these problems, existing technologies have developed a variety of scaffolding-free mechanized construction methods.

[0003] For example, in the construction of high slopes in pumped storage power stations, high-lift slope anchoring drilling rigs have been used to replace traditional scaffolding, enabling rapid hole drilling and providing a working platform. For drilling on high slopes with fractured surrounding rock, some technologies have proposed using simple operating platforms to shorten the construction period, save costs, reduce labor intensity and safety risks. In addition, there is the scaffolding-free controlled blasting layer-by-layer support technology for high and steep slopes, which utilizes the in-situ strata as a construction platform by pre-splitting to the bottom in one go, excavating in layers, and supporting layer by layer, thus avoiding the safety hazards and time consumption of scaffolding.

[0004] These existing technologies have achieved significant results in improving construction efficiency and reducing safety risks. However, with the increasing complexity of engineering geological conditions and the continuous improvement of requirements for construction efficiency, quality, safety, and environmental protection, there is still room for improvement in the deep integration of existing technologies in mechanization, automation, and intelligence. Specifically, existing mechanization is mainly concentrated in single links, lacking multi-task integration and intelligent collaboration capabilities; safety monitoring is mostly post-event analysis or passive early warning, lacking mechanisms for proactive identification, prediction, and intervention; material proportions rely heavily on experience or presets, failing to adapt to real-time geological and environmental changes; and construction process data has not been effectively integrated and utilized, making it difficult to support intelligent optimization and decision-making based on big data. Summary of the Invention

[0005] To address the problems mentioned in the background art, such as low construction efficiency, high construction safety risks, insufficient mechanization and intelligence, inability to adapt material ratios, and failure to effectively utilize construction data to support intelligent optimization, this application provides a rapid prototyping construction method for high slopes based on scaffold-free mechanization.

[0006] This application provides a rapid prototyping construction method for high slopes based on scaffold-free mechanized construction, which adopts the following technical solution: A rapid prototyping construction method based on scaffold-free mechanized construction of high slopes includes the following steps: Step 1: High-precision holographic digital modeling and intelligent planning of slopes; 3D point cloud data of slopes are obtained through UAV laser scanning and oblique photography, and a high-precision 3D geological model is constructed by combining geological exploration data. Multi-source data are integrated to form a digital twin, and artificial intelligence algorithms are used to optimize blasting parameters, robot operation paths, material transportation scheduling and layered and zoned construction strategies. Step 2: Deployment of a multi-functional intelligent robot platform and geological adaptive drilling; Autonomous navigation and positioning are achieved by using a tracked or multi-legged robot platform combined with LiDAR and visual SLAM technology, and the intelligent drilling module is used to automatically identify geological differences and adaptively adjust drilling modes and parameters by combining real-time drilling parameters and geophysical exploration data in the borehole. Step 3: Adaptive material ratio; Based on the real-time geological parameters of the slope obtained from drilling and monitoring data, combined with an artificial intelligence ratio optimization model, the ratio of anchoring grout and shotcrete is automatically recommended. The automated preparation system is used to accurately prepare the material according to the plan, and the quality is controlled by sensors. Step 4: Automated anchoring, intelligent spraying and intelligent material conveying; The installation, grouting and tensioning of anchor bolts are completed automatically through a robotic platform. Thickness-adaptive spraying is achieved by using 3D vision scanning combined with a spraying robotic arm, and continuous material supply is achieved through an automatic conveying system. Step 5: Intelligent safety monitoring and risk warning throughout the entire lifecycle; integrate monitoring data, equipment data, personnel data and meteorological data to build a safety situation awareness system, use artificial intelligence for risk identification and early warning, and support intelligent emergency response, remote inspection and safety management optimization.

[0007] By adopting the above technical solutions, high-precision digital modeling of slopes is integrated with multi-source data to achieve full-process visualization, predictability, and optimizable management of construction. By utilizing digital twins and intelligent planning, blasting, robotic operations, material transportation, and layered construction are closely coordinated, reducing conflicts between construction procedures and improving operational continuity and resource utilization efficiency. At the same time, by integrating safety monitoring and dynamic decision-making, this method enables proactive risk identification and intervention, thereby improving overall construction efficiency, project quality, and safety.

[0008] Optionally, the UAV laser scanning in step one uses a combination of lidar and multispectral cameras, achieving point cloud accuracy at the centimeter level. The geological exploration data includes the lithological characteristics, mechanical parameters, distribution of bedding joints and faults, information on weak interlayers and fracture zones of the rock and soil, as well as hydrogeological conditions such as groundwater level, water content and permeability. The mathematical construction form of a digital twin formed by integrating multi-source data can be described as follows: ; in, It is a three-dimensional geometric model. It is a geomechanical parameter field (including lithology, joints, water-bearing capacity, etc.). This is a historical monitoring sequence. This is a dynamic interface function used to receive real-time sensor data during construction and update the twin's state.

[0009] By adopting the above technical solutions, construction personnel can accurately grasp the complex geological characteristics of the slope, providing a reliable foundation for drilling, grouting and support, reducing construction errors and safety hazards caused by unclear geology, and improving project reliability and construction preparation efficiency.

[0010] Optionally, the intelligent construction planning in step one employs genetic algorithms or reinforcement learning methods to perform multi-objective optimization of blasting parameters, operation paths, and material scheduling, specifically including: Blasting parameter optimization: Simulate the impact of different blasting parameters on slope stability and excavation effect, predict blasting vibration, and optimize the blasting scheme with minimum disturbance and maximum efficiency. The blasting parameters include blasting hole location, hole depth, charge amount and detonation sequence. Robot operation path planning: Plan the optimal movement path and operation sequence of the multi-functional intelligent robot operation platform on the slope to avoid operation conflicts and maximize operation efficiency; Material transportation and resource scheduling: Optimize the transportation routes and scheduling plans for anchor bolts, steel mesh, concrete, and grout to ensure the timely supply of construction materials; Layered and zoned construction strategy: Develop a refined layered and zoned construction strategy to ensure seamless connection and efficient parallel operation of excavation, support, monitoring and other processes; The optimization process, centered on minimizing (perturbation, cost, risk) and maximizing (efficiency, safety) objective functions, can be described as follows: ; in, This represents the set of construction parameters (including blasting parameters, robot operation paths, material scheduling schemes, and layering / zoning strategies). , , , These represent the blasting disturbance function, the robot operation path efficiency function, the material supply timeliness function, and the layered construction coordination function, respectively. , , , Optimize weights for multiple objectives.

[0011] By adopting the above technical solutions and utilizing genetic algorithms or reinforcement learning to perform multi-objective optimization of blasting parameters, robot operation paths, material transportation, and layered and zoned construction strategies, the effects of different schemes can be simulated before construction, slope vibration and operational efficiency can be predicted, and optimal configuration of construction parameters can be achieved. This method can effectively reduce slope disturbance, lower safety risks, and maximize construction efficiency. In addition, by optimizing material transportation paths and layered and zoned strategies, resource waste can be reduced, construction period can be shortened, and seamless connection between various processes can be ensured.

[0012] Optionally, the multifunctional intelligent robot operating platform in step two is a tracked or multi-legged chassis, which combines LiDAR and visual synchronous positioning and mapping to achieve centimeter-level positioning and autonomous attitude adjustment.

[0013] By adopting the above technical solutions, tracked or multi-legged robot platforms, combined with LiDAR and visual SLAM, achieve autonomous navigation and centimeter-level positioning. They can also automatically adjust their posture according to slope gradient and terrain changes, ensuring the stability and safety of the work platform. This allows the robot to operate efficiently on complex and steep terrain, avoiding the safety risks of manual climbing construction. At the same time, autonomous navigation and positioning technologies improve operational accuracy, providing reliable support for subsequent construction stages such as drilling, spraying, and anchoring, thereby improving construction efficiency and support quality, and reducing the probability of accidents.

[0014] Optionally, the drilling parameters in step two include drilling speed, torque, and axial pressure, and the in-hole geophysical exploration data includes acoustic and resistivity parameters. Based on the drilling parameters and in-hole geophysical exploration data, rock fracture zones, fissures, and water-rich areas are identified, and the impact rotary or casing drilling mode is adaptively selected according to geological differences.

[0015] By adopting the above technical solutions and utilizing real-time drilling parameters and geophysical exploration data within the borehole, the system can automatically identify fractured zones, fissures, and water-rich areas in the rock mass, and adaptively adjust the drilling mode. This effectively avoids problems such as borehole collapse, stuck drill bits, and construction delays, improving the safety and continuity of drilling operations. In particular, intelligent drilling not only improves drilling accuracy but also ensures the construction quality of subsequent anchoring, grouting, and shotcreting materials, providing reliable support for high slope construction, significantly reducing manual intervention and operational risks, and realizing intelligent and efficient construction processes.

[0016] Optionally, the real-time geological parameters of the slope in step three include the degree of rock mass fragmentation, fissure development, groundwater conditions, and surrounding rock stress state; Based on real-time geological parameters of the slope, the required performance data of the anchoring grout and shotcrete are obtained, including grout strength, toughness, impermeability, setting time and early strength. Based on the required anchoring grout and shotcrete, the artificial intelligence mix optimization model automatically recommends the mix ratio of anchoring grout and shotcrete, including cement type and dosage, aggregate gradation, admixture type and dosage, and water-cement ratio.

[0017] By adopting the above technical solutions, the material properties are highly matched with the actual construction needs, ensuring that the grout and concrete meet the design requirements in terms of strength, toughness, impermeability, setting time and early strength, thereby improving the durability and stability of the support structure. At the same time, the dynamic adjustment and precise control of the material ratio are realized, avoiding the uncertainty and waste of resources of traditional experience-based ratios, and helping to improve construction efficiency and construction quality.

[0018] Optionally, the automated preparation system in step three includes an intelligent mixing station and online sensors. According to the recommended mixing ratio, it accurately measures and mixes various raw materials to achieve intelligent preparation of slurry and concrete. The temperature, consistency and fluidity of the slurry or concrete are monitored in real time by sensors.

[0019] By adopting the above technical solutions, raw materials can be accurately measured and mixed according to the recommended ratio, and the temperature, consistency and fluidity of the slurry or concrete can be monitored in real time. This ensures the stability and uniformity of the material preparation process, reduces human error, and improves the quality of construction materials. This automated preparation system, combined with real-time sensor monitoring, realizes the intelligence and reliability of material preparation, provides high-quality material guarantee for subsequent spraying and anchoring construction, improves construction efficiency and reduces material waste.

[0020] Optionally, the automated anchoring in step four involves monitoring the grouting process using flow and pressure sensors, and utilizing force sensors to provide real-time feedback and automatically record tension data during the tensioning process.

[0021] By adopting the above technical solutions, automated anchoring monitors the grouting process in real time through flow and pressure sensors, and uses force sensors to provide feedback and automatically record data during the tensioning process. This ensures the fullness of grouting and the accuracy of prestressing tension, effectively avoiding support defects caused by improper human operation, ensuring uniform stress on the anchoring structure, and improving the overall stability and reliability of the support system. At the same time, the automatic recording and feedback function provides traceable data for the construction process, enabling controllable and verifiable construction quality and improving construction safety.

[0022] Optionally, the intelligent spraying module in step four acquires the slope surface morphology and sprayed thickness in real time through a three-dimensional vision scanning system, and automatically adjusts the nozzle angle, distance and flow rate according to the thickness requirements to achieve adaptive control of the sprayed layer thickness.

[0023] By adopting the above technical solution, the surface morphology and sprayed thickness of the slope are obtained by three-dimensional visual scanning, and the nozzle angle, distance and flow rate are automatically adjusted to achieve adaptive control of the sprayed layer thickness. This ensures that the thickness of the sprayed concrete or grout is more uniform and dense, and can compensate for local irregular areas to improve the support quality. This automated spraying and thickness feedback control method can reduce human operation errors, improve the efficiency of spraying construction and material utilization, and at the same time ensure the safety and durability of the support structure.

[0024] Optionally, the risk warning system in step five combines slope deformation monitoring, mechanical condition detection, personnel behavior recognition, and meteorological factors, and uses deep learning for multi-source fusion analysis to predict and warn of slope instability, mechanical failure, unsafe personnel behavior, and extreme weather risks.

[0025] By adopting the above technical solutions, proactive prediction and early warning can be made for slope instability, mechanical failure, unsafe behavior of personnel, and extreme weather risks. It is mainly used to realize the safety situation perception and intelligent management of construction sites, which can trigger emergency response in a timely manner, reduce the probability of accidents, and provide decision support for managers. Overall, it can significantly improve the safety, controllability, and intelligent management level of high slope construction.

[0026] In summary, this application includes at least one of the following beneficial technical effects: This invention achieves close collaboration and conflict-free operation in the construction process by combining high-precision digital modeling of slopes with intelligent construction planning and artificial intelligence algorithms to optimize blasting parameters, robot operation paths, material transportation and layered construction strategies. Furthermore, this method can simulate different schemes before construction, predict slope vibration and operation efficiency, thereby shortening the construction period, reducing resource waste, and significantly improving construction continuity and overall efficiency.

[0027] This invention employs a multi-functional intelligent robot platform combined with lidar and visual SLAM to achieve autonomous navigation, centimeter-level positioning, and attitude adaptation. Meanwhile, the intelligent drilling module can identify rock fracture zones, fissures, and water-rich areas in real time and adaptively select drilling modes, effectively reducing human intervention, improving the stability of the work platform, significantly reducing construction risks, and ensuring the safe conduct of drilling, anchoring, and shotcreting operations.

[0028] This invention is based on real-time slope geological parameters and an artificial intelligence mix optimization model. It automatically recommends the mix ratio of anchoring grout and shotcrete, and accurately prepares and monitors it through an intelligent mixing plant and online sensors. Combined with an automated anchoring and intelligent shotcreting system, it can achieve a high degree of matching between material properties and construction requirements, ensuring that the support structure meets design requirements in terms of strength, toughness, impermeability and early strength, thereby improving structural durability and construction quality.

[0029] This invention utilizes a full lifecycle safety monitoring system that integrates slope deformation, equipment status, personnel behavior, and meteorological data. By employing deep learning for multi-source analysis, it enables the prediction and early warning of slope instability, mechanical failures, unsafe personnel behavior, and extreme weather. Simultaneously, this invention organically combines digital modeling, robotic operations, material preparation, and automatic spraying systems to form an intelligent overall system for high slope construction, thereby improving construction management, safety, and intelligence. Attached Figure Description

[0030] Figure 1 This is a system flowchart of the present invention. Detailed Implementation

[0031] The present application will be further described in detail below with reference to the accompanying drawings.

[0032] As shown in the figure, this application discloses a rapid prototyping construction method based on high slope scaffolding-free mechanization, including the following steps: Step 1: High-precision holographic digital modeling and intelligent planning of slopes; Step Two: Deployment of the multi-functional intelligent robot operation platform and geological adaptive drilling; Step 3: Adaptive material proportioning; Step 4: Automated anchoring, intelligent spraying, and intelligent material delivery; Step 5: Intelligent security monitoring and risk warning throughout the entire lifecycle.

[0033] Specifically, in step one, a drone equipped with a high-precision lidar and multispectral camera is used to perform a comprehensive scan and photography of the high slope, acquiring centimeter-level three-dimensional point cloud data and high-resolution images of the slope surface. Simultaneously, combined with geological exploration data, an initial high-precision three-dimensional geological model of the slope is constructed to accurately identify key geological information such as rock mass structure, fracture distribution, faults, weak interlayers, and groundwater occurrence. This geological exploration data includes lithological characteristics, mechanical parameters, distribution of bedding joints and faults, information on weak interlayers and fracture zones, as well as hydrogeological conditions such as groundwater level, water content, and permeability.

[0034] Geometric data collected by drones Geological exploration data Historical monitoring data The data fusion process involves spatiotemporal alignment, feature extraction, and weighted coupling to form a unified parameterized expression, which can be mathematically described as follows: ; in, , , These represent operators for geometric feature extraction, geological attribute analysis, and time series monitoring modeling, respectively. , , These are the fusion weight coefficients determined through entropy weighting or minimum mean square error optimization. This results in fused data. It maintains consistency and updability in both the spatial dimension (x, y, z) and the temporal dimension (t).

[0035] Based on the aforementioned fused data, an initial holographic digital twin of the slope is constructed. This digital twin not only includes the static geometric and geological properties of the slope but also possesses a real-time data interface, preparing for the injection of dynamic data during subsequent construction. Its mathematical construction form is described as follows: ; in, It is a three-dimensional geometric model. It is a geomechanical parameter field (including lithology, joints, water-bearing capacity, etc.). This is a historical monitoring sequence. This is a dynamic interface function used to receive real-time sensor data during construction and update the digital twin's state. Through this structure, the digital twin possesses both static configuration and dynamic evolution characteristics.

[0036] Based on this, the constructed digital twin The use of artificial intelligence algorithms (such as genetic algorithms and reinforcement learning) for intelligent planning and optimization of construction schemes includes: Blasting parameter optimization: Simulate the impact of different blasting parameters (hole location, hole depth, charge amount, detonation sequence) on slope stability and excavation effect, predict blasting vibration, and optimize the blasting scheme with minimum disturbance and maximum efficiency. Specifically, the disturbance to the slope caused by blasting operations during construction can be described as follows: ; in, This represents the set of blasting parameters (hole location, hole depth, charge amount, detonation sequence); Indicates the explosive energy or charge quantity; The exponential factor represents the nonlinear relationship of the blasting effect; This indicates a coefficient adjusted based on slope characteristics.

[0037] Robot operation path planning: Planning the optimal movement path and operation sequence of a multi-functional intelligent robot operation platform on a slope to avoid operation conflicts and maximize operation efficiency; it can be described as: ; This represents the total length of the robot's movement path on the slope, calculated by a path planning algorithm.

[0038] Material transportation and resource scheduling: Optimize the transportation routes and scheduling schemes for anchor bolts, steel mesh, concrete, and grout to ensure timely supply of construction materials; specifically, the total delay in the supply of construction materials can be described as follows: ; in, Indicates the actual number Arrival time of the batch of materials; Indicates the plan number Arrival time of the batch of materials; Indicates the quantity of materials in a batch.

[0039] The greater the latency, the lower the efficiency.

[0040] Layered and zoned construction strategy: A refined layered and zoned construction strategy is developed to ensure seamless integration and efficient parallel operation of excavation, support, and monitoring processes. During layered construction, the sum of coordination deviations across each zone can be described as follows: ; in, Indicates the first Deviations in coordination between different construction zones; Indicates the number of partitions.

[0041] This function is used to measure the coordination of layered and zoned construction; the smaller the deviation, the better.

[0042] More specifically, the optimization process, centered on minimizing (perturbation, cost, risk) and maximizing (efficiency, safety) objective functions, can be described as follows: ; in, This represents the set of construction parameters (including blasting parameters, robot operation paths, material scheduling schemes, and layering / zoning strategies). , , , These represent the blasting disturbance function, the robot operation path efficiency function, the material supply timeliness function, and the layered construction coordination function, respectively. , , , Optimize weights for multiple objectives.

[0043] The optimization algorithm can employ genetic algorithms (GA) or reinforcement learning (RL), gradually converging to the optimal solution through iterative learning and simulation feedback. .

[0044] Ultimately, the optimal construction plan is as follows: This scheme can ensure that, while satisfying the requirements of slope stability and safety, it achieves the overall optimal balance between construction efficiency and resource utilization.

[0045] Specifically, in step two, the deployment of the multi-functional intelligent robot operation platform and the geological adaptive drilling method are as follows: the modularly designed multi-functional intelligent robot operation platform is deployed to the designated location on the slope. The platform adopts a tracked or multi-legged chassis and combines LiDAR and visual simultaneous localization and mapping (SLAM) technology to achieve autonomous navigation and centimeter-level precise positioning on complex and steep terrain. The platform can adjust its attitude in real time according to the slope gradient, terrain undulation, etc. to ensure operational stability.

[0046] The intelligent drilling module is activated. This module is equipped with a high-precision real-time dynamic positioning system (RTK-GNSS) or a laser scanning positioning system to ensure precise control of the borehole position, angle, and depth. During drilling, the module automatically identifies rock fracture zones, fissures, and water-rich areas by analyzing drilling parameters (such as drilling speed, torque, and axial pressure) and geophysical exploration data (such as acoustic waves and resistivity) in real time. Based on the identification results, the system automatically adjusts the drilling mode (such as impact rotation and casing drilling) and parameters to effectively avoid borehole collapse and stuck drill, achieving adaptive drilling under geological conditions.

[0047] Specifically, in step three, the adaptive material ratio method is as follows: Using the borehole core images, drilling parameters, and geophysical exploration data obtained by the intelligent drilling module in step two, as well as real-time data such as slope deformation and water content provided by the intelligent monitoring module, the system comprehensively perceives the real-time geological conditions of the slope (e.g., rock mass fracturing degree, fissure development, groundwater conditions, and surrounding rock stress state). Based on this data, the system intelligently analyzes the current area's performance requirements for anchoring grout and shotcrete (e.g., strength, toughness, impermeability, setting time, and early strength).

[0048] Subsequently, a material proportioning optimization model based on massive historical data and machine learning algorithms was established. This model takes real-time sensed geological parameters and material performance requirements as input, and through deep learning and predictive analysis, automatically recommends the optimal anchoring grout and shotcrete proportioning schemes. Specifically, it includes: cement type and dosage, aggregate gradation, admixture (such as accelerator, water-reducing agent, and expansion agent) type and dosage, and water-cement ratio. This model can achieve a breakthrough in traditional experience-based proportioning, and achieve more accurate and efficient material performance customization.

[0049] Finally, an automated material preparation system (such as an intelligent mixing plant) is installed, which can accurately measure and mix various raw materials according to the proportioning scheme recommended by artificial intelligence, so as to realize the intelligent preparation of slurry and concrete. During the preparation process, sensors monitor key physical parameters such as temperature, consistency and fluidity of materials in real time to ensure that the preparation quality meets the requirements. The prepared materials are directly transported to the work surface through an intelligent conveying system.

[0050] Specifically, in step four, the methods for automated anchoring, intelligent spraying, and intelligent material delivery are as follows: the intelligent robot operation platform automatically delivers the precast anchor rods or anchor cables to the borehole and precisely inserts them into the borehole; the automated grouting system automatically grouts according to the intelligently proportioned grout from step three, and monitors the grouting process in real time through flow and pressure sensors to ensure the fullness and uniformity of the grout; after the grout reaches the design strength, the intelligent tensioning module automatically performs prestressing tensioning, and provides real-time feedback of the tensioning force through a high-precision force sensor to ensure the accuracy of prestressing application, and automatically records the tensioning data.

[0051] The intelligent spraying module is equipped with a multi-axis robotic arm and a 3D vision scanning system to acquire the slope surface morphology and the thickness of the sprayed layer in real time. Based on the scanning data and design requirements, it automatically plans the spraying path and adjusts the distance, angle and spraying flow rate between the nozzle and the slope in real time to ensure that the concrete or grout sprayed layer is uniform and dense, and minimizes rebound. For local over-excavation or irregular areas, the system can automatically identify and perform local thickening spraying to achieve thickness self-adaptation.

[0052] The platform integrates automated material conveying modules (such as self-climbing cableways or tracked conveyor vehicles) to automatically and continuously transport materials such as anchor bolts, steel mesh, ready-mixed concrete, or grout to the work site according to the construction schedule and requirements, reducing manual handling and improving efficiency and safety. The conveying process is uniformly managed by an intelligent scheduling system to ensure smooth material flow.

[0053] Specifically, in step five, the solution for intelligent safety monitoring and risk early warning throughout the entire lifecycle is as follows: integrate monitoring data, equipment data, personnel data, and meteorological data to build a safety situation awareness system, use artificial intelligence for risk identification and early warning, and support intelligent emergency response, remote inspection, and safety management optimization.

[0054] More specifically, multi-source safety-related data from intelligent monitoring modules (slope deformation, internal stress, pore water pressure, environmental parameters), intelligent robot operation platforms (equipment status, operating parameters, operational behavior), personnel wearable devices (heart rate, location, fall detection, gas concentration), high-definition video monitoring systems (work area, personnel activity, abnormal events), and weather stations (wind speed, rainfall, temperature) are aggregated, cleaned, and stored in real time through a big data platform to build a comprehensive safety situation awareness capability.

[0055] By leveraging deep learning, anomaly detection, and predictive analytics, integrated data is analyzed in real time to proactively identify potential security risks. For example: Slope instability risk prediction: Based on slope deformation data, geological models and environmental factors, predict the possibility and trend of local or overall slope instability, and conduct graded early warning; Mechanical Failure Early Warning: Monitor the operating parameters of key components of the robot's work platform, predict potential failures, and perform maintenance in advance; Personnel Behavior Risk Identification: Through video analysis and wearable device data, unsafe behaviors of personnel (such as not wearing safety belts, entering dangerous areas, and working while fatigued) are identified, and real-time reminders and corrections are provided; Environmental risk assessment: Based on meteorological data, assess the impact of extreme weather (such as heavy rain and strong winds) on construction safety and provide operational recommendations.

[0056] The system can automatically trigger different levels of early warning based on the risk level, and promptly notify relevant personnel and on-site workers through various means such as audible and visual alarms, SMS, application push notifications, and drone announcements.

[0057] When a safety incident occurs (such as minor slippage, mechanical failure, or personnel injury), the system can automatically locate the incident site and, according to a pre-set emergency plan, automatically deploy nearby emergency robots (such as reconnaissance and rescue robots) to conduct on-site reconnaissance, data collection, and preliminary handling (such as deploying temporary supports and isolating dangerous areas). Simultaneously, the system sends detailed information and real-time video to the emergency command center to assist decision-makers in quickly developing rescue plans and coordinating multiple rescue forces.

[0058] Furthermore, in-depth analysis of historical safety incident data, risk warning records, and personnel behavior data can be conducted to assess the effectiveness of various safety management measures. Through visualized reports and analysis results, high-risk work processes, equipment, and personnel can be identified, and targeted safety training, management system, and technical improvement suggestions can be proposed to achieve continuous optimization and iterative upgrading of the safety management system.

[0059] Managers and safety experts can conduct remote safety inspections using the holographic digital twin system, view the three-dimensional safety situation of the construction site in real time, access historical data and videos, and perform safety assessments and management. The system also supports remote safety meetings and collaborative decision-making, improving the efficiency and coverage of safety management.

[0060] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A rapid prototyping construction method based on scaffold-free mechanized construction of high slopes, characterized in that, Includes the following steps: Step 1: High-precision holographic digital modeling and intelligent planning of slopes; 3D point cloud data of slopes are obtained through UAV laser scanning and oblique photography, and a high-precision 3D geological model is constructed by combining geological exploration data. Multi-source data are integrated to form a digital twin, and artificial intelligence algorithms are used to optimize blasting parameters, robot operation paths, material transportation scheduling and layered and zoned construction strategies. Step 2: Deployment of a multi-functional intelligent robot platform and geological adaptive drilling; Autonomous navigation and positioning are achieved by using a tracked or multi-legged robot platform combined with LiDAR and visual SLAM technology, and the intelligent drilling module is used to automatically identify geological differences and adaptively adjust drilling modes and parameters by combining real-time drilling parameters and geophysical exploration data in the borehole. Step 3: Adaptive material proportioning; Based on real-time geological parameters of the slope obtained from borehole and monitoring data, and combined with an artificial intelligence mix optimization model, the mix ratio of anchoring grout and shotcrete is automatically recommended. The automated preparation system is used to accurately prepare the grout according to the plan and the quality is controlled by sensors. Step 4: Automated anchoring, intelligent spraying and intelligent material conveying; The installation, grouting and tensioning of anchor bolts are completed automatically through a robotic platform. Thickness-adaptive spraying is achieved by using 3D vision scanning combined with a spraying robotic arm, and continuous material supply is achieved through an automatic conveying system. Step 5: Intelligent safety monitoring and risk warning throughout the entire lifecycle; integrate monitoring data, equipment data, personnel data and meteorological data to build a safety situation awareness system, use artificial intelligence for risk identification and early warning, and support intelligent emergency response, remote inspection and safety management optimization.

2. The rapid prototyping construction method based on scaffold-free mechanized construction of high slopes according to claim 1, characterized in that, The UAV laser scanning in step one uses a combination of lidar and multispectral cameras, achieving point cloud accuracy at the centimeter level. The geological exploration data includes the lithological characteristics, mechanical parameters, distribution of bedding joints and faults, information on weak interlayers and fracture zones of the rock and soil, as well as hydrogeological conditions such as groundwater level, water content and permeability. The mathematical construction form of a digital twin formed by integrating multi-source data can be described as follows: ； in, It is a three-dimensional geometric model. It is a geomechanical parameter field (including lithology, joints, water-bearing capacity, etc.). This is a historical monitoring sequence. This is a dynamic interface function used to receive real-time sensor data during construction and update the twin's state.

3. The rapid prototyping construction method based on scaffold-free mechanized construction of high slopes according to claim 1, characterized in that, The intelligent construction planning in step one employs genetic algorithms or reinforcement learning methods to perform multi-objective optimization of blasting parameters, operation paths, and material scheduling, specifically including: Blasting parameter optimization: Simulate the impact of different blasting parameters on slope stability and excavation effect, predict blasting vibration, and optimize the blasting scheme with minimum disturbance and maximum efficiency. The blasting parameters include blasting hole location, hole depth, charge amount and detonation sequence. Robot operation path planning: Plan the optimal movement path and operation sequence of the multi-functional intelligent robot operation platform on the slope to avoid operation conflicts and maximize operation efficiency; Material transportation and resource scheduling: Optimize the transportation routes and scheduling plans for anchor bolts, steel mesh, concrete, and grout to ensure the timely supply of construction materials; Layered and zoned construction strategy: Develop a refined layered and zoned construction strategy to ensure seamless connection and efficient parallel operation of excavation, support, monitoring and other processes; The optimization process, centered on minimizing and maximizing the objective function, can be described as follows: ； in, This represents the set of construction parameters (including blasting parameters, robot operation paths, material scheduling schemes, and layering / zoning strategies). , , , These represent the blasting disturbance function, the robot operation path efficiency function, the material supply timeliness function, and the layered construction coordination function, respectively. , , , Optimize weights for multiple objectives.

4. The rapid prototyping construction method based on scaffold-free mechanized construction of high slopes according to claim 1, characterized in that, The multifunctional intelligent robot operating platform in step two is a tracked or multi-legged chassis, which combines lidar and visual synchronous positioning and map building to achieve centimeter-level positioning and autonomous attitude adjustment.

5. The rapid prototyping construction method based on scaffold-free mechanized construction of high slopes according to claim 1, characterized in that, The drilling parameters in step two include drilling speed, torque, and axial pressure. The in-hole geophysical exploration data includes acoustic and resistivity parameters. Based on the drilling parameters and in-hole geophysical exploration data, rock fracture zones, fissures, and water-rich areas are identified, and the impact rotary or casing drilling mode is adaptively selected according to geological differences.

6. The rapid prototyping construction method based on scaffold-free mechanized construction of high slopes according to claim 1, characterized in that, The real-time geological parameters of the slope in step three include the degree of rock fragmentation, fissure development, groundwater conditions, and surrounding rock stress state. Based on real-time geological parameters of the slope, the required performance data of the anchoring grout and shotcrete are obtained, including grout strength, toughness, impermeability, setting time and early strength. Based on the required anchoring grout and shotcrete, the artificial intelligence mix optimization model automatically recommends the mix ratio of anchoring grout and shotcrete, including cement type and dosage, aggregate gradation, admixture type and dosage, and water-cement ratio.

7. A rapid prototyping construction method based on scaffold-free mechanized construction of high slopes according to claim 6, characterized in that, The automated preparation system in step three includes an intelligent mixing station and online sensors. According to the recommended mixing ratio, it accurately measures and mixes various raw materials to achieve intelligent preparation of slurry and concrete. The sensors also monitor the temperature, consistency and fluidity of the slurry or concrete in real time.

8. The rapid prototyping construction method based on scaffold-free mechanized construction of high slopes according to claim 1, characterized in that, The automated anchoring in step four monitors the grouting process using flow and pressure sensors, while the tensioning process utilizes force sensors to provide real-time feedback and automatically record tensioning data.

9. The rapid prototyping construction method based on scaffold-free mechanized construction of high slopes according to claim 1, characterized in that, The intelligent spraying module in step four uses a three-dimensional vision scanning system to acquire the slope surface morphology and the thickness of the sprayed layer in real time, and automatically adjusts the nozzle angle, distance and flow rate according to the thickness requirements to achieve adaptive control of the sprayed layer thickness.

10. The rapid prototyping construction method based on scaffold-free mechanized construction of high slopes according to claim 1, characterized in that, The risk warning system in step five combines slope deformation monitoring, mechanical condition detection, personnel behavior identification, and meteorological factors. It uses deep learning for multi-source fusion analysis to predict and warn of slope instability, mechanical failure, unsafe personnel behavior, and extreme weather risks.

Images