Slope monitoring point arrangement method and system for whole construction and operation cycle

Abstract

This invention relates to the field of geotechnical engineering monitoring and slope stability analysis technology, specifically to a method and system for the layout of slope monitoring points throughout the entire construction and operation cycle. The method acquires multi-source monitoring data and constructs a unified data warehouse through cleaning, format conversion, and spatiotemporal registration. Based on this unified data warehouse, a dynamic risk assessment model coupled with the limit equilibrium method and the finite element method is used to identify target risk areas, and key monitoring variables are identified through global sensitivity analysis. Finally, a multi-objective optimization algorithm is used to solve for the Pareto optimal solution set to determine the location and density of monitoring points. This invention achieves adaptive matching of the monitoring network to changes in geological conditions and dynamic engineering needs throughout the entire cycle, improving the targeting of monitoring and the efficiency of resource allocation.

Description

Technical Field

[0001] This invention relates to the field of geotechnical engineering monitoring and slope stability analysis technology, and in particular to a method and system for arranging slope monitoring points throughout the entire construction and operation cycle. Background Technology

[0002] Traditional slope monitoring point layout methods have significant drawbacks in the monitoring of steep slopes in highways, railways, water conservancy, and mining projects. Firstly, the monitoring network is often statically deployed only during the survey and design phase, failing to adapt to dynamic changes in stress and strain fields caused by excavation and blasting during construction, and also struggling to match the long-term impact of environmental factors during operation, easily leading to monitoring blind spots or resource waste. Secondly, the layout scheme heavily relies on engineers' personal experience, lacking scientific quantitative basis, and is highly subjective, making it difficult to address the coverage needs of potential risk points under complex geological conditions. Thirdly, existing technologies lack dynamic feedback and adaptive optimization mechanisms, unable to adjust the monitoring network based on newly revealed geological information during construction, abnormal monitoring data, or extreme weather and long-term creep during operation, resulting in insufficient continuity of monitoring data and limited accuracy in long-term stability assessment. Furthermore, existing optimization methods often focus on a single objective, making it difficult to balance monitoring effectiveness with monitoring resource investment, further limiting the practicality of the monitoring system. Therefore, a slope monitoring point layout method that adapts to the entire construction and operation cycle and possesses dynamic adaptive capabilities is urgently needed.

[0003] Existing patent CN119962136B discloses a method for dynamically optimizing the layout of monitoring points on high slopes. This method includes acquiring multi-source monitoring data for each monitoring point among multiple monitoring points in a high slope monitoring area; determining the neighborhood radius and feature density of each monitoring point based on the multi-source monitoring data, and partitioning the monitoring area according to the neighborhood radius and feature density; acquiring the partition features of each partition, and inputting the partition features and multi-source monitoring data into a deep learning model based on an attention mechanism to obtain the importance score and stable state of each partition; and determining an optimization strategy for deploying monitoring points in each partition based on the importance score, stable state, and feature density. However, this patent lacks optimization of the monitoring layout scheme for multi-objective constraints and lacks adaptive adjustment rules for different stages throughout the construction and operation cycle, making it difficult to maximize resource utilization efficiency while ensuring monitoring coverage. Summary of the Invention

[0004] The purpose of this invention is to overcome the technical problems of existing slope monitoring point layout, such as static monitoring network, strong reliance on experience, and lack of dynamic adaptive optimization capability throughout the entire cycle. It provides a method and system for slope monitoring point layout that is oriented towards the entire construction and operation cycle.

[0005] In a first aspect, the present invention provides a method for arranging slope monitoring points throughout the entire construction and operation cycle, the method comprising the following steps:

[0006] S1. Obtain multi-source monitoring data of the slope, perform data cleaning, format conversion and spatiotemporal registration on the above multi-source data, and build a unified data warehouse; S2. Based on the above unified data warehouse, a dynamic risk assessment model coupled with the limit equilibrium method and the finite element method is used to calculate the failure probability of different areas of the slope and identify the target risk area; the global sensitivity analysis method is used to calculate the sensitivity index of each monitoring parameter in the above unified data warehouse to the slope safety factor and identify key monitoring variables. S3. Based on the above target risk areas and the above key monitoring variables, a multi-objective optimization algorithm is used to solve for the Pareto optimal solution set, and the location and density of monitoring points are determined.

[0007] Through a collaborative process of multi-source data integration, dynamic risk assessment, sensitivity analysis, and multi-objective optimization, the layout of monitoring points is precisely matched with the dynamic changes in the entire project cycle and geological conditions, thereby improving the targeting of monitoring and optimizing resource allocation.

[0008] Preferably, the aforementioned multi-source monitoring data includes basic static data and dynamically updated data; The aforementioned basic static data includes GIS 3D topographic model data of the slope area, slope engineering geological survey data, slope engineering design documents, and historical slope disaster data of the slope area; the aforementioned slope engineering geological survey data includes at least one of the following: physical and mechanical parameters of soil and rock mass, geological structure distribution data, and detection data of weak interlayers and potential sliding surfaces; the aforementioned slope engineering design documents include at least one of the following: slope geometry design drawing, support structure design drawing, and preliminary monitoring layout plan drawing; the aforementioned historical slope disaster data includes at least one of the following: occurrence time, location, scale, and triggering factors of landslides and collapses. The aforementioned dynamically updated data includes slope construction progress data and real-time monitoring data of the slope body and surrounding environment; the aforementioned construction progress data includes at least one of the following: graded excavation process plan, support structure construction progress, and blasting operation plan; the aforementioned real-time monitoring data of the slope body and surrounding environment includes at least one of the following: slope displacement data, rock and soil stress and strain data, slope and surrounding hydrological data, and environmental meteorological data.

[0009] By clearly defining the classification and specific content of multi-source monitoring data, comprehensive and accurate basic data support is provided for a unified data warehouse, ensuring the reliability of subsequent risk assessment and optimization calculations.

[0010] Preferably, in S1: data cleaning of the above multi-source data is performed using 3... The criteria or box plot method are used to remove outlier data points and noisy data; the above format conversion converts the above multi-source monitoring data into the IFC standard format; the above spatiotemporal registration adopts geodetic coordinate system transformation technology and time scale alignment technology; when constructing the above unified data warehouse, the data fusion method used is at least one of ontology-based data fusion method, XML-based data fusion method, RDF-based semantic data fusion method and knowledge graph-based association data fusion method.

[0011] By using standardized data cleaning, format conversion, spatiotemporal registration, and fusion methods, we can eliminate format differences, spatiotemporal deviations, and quality risks associated with multi-source data.

[0012] Preferably, in S2: the dynamic risk assessment model can be replaced by at least one of the reliability index method, response surface methodology, and support vector machine risk prediction model; the global sensitivity analysis method can be replaced by at least one of the Morris screening method, FAST method, and local sensitivity analysis method.

[0013] By providing alternatives to dynamic risk assessment models and sensitivity analysis methods, the adaptability of the methods is enhanced, and the technical path can be flexibly selected according to the project scale and data conditions.

[0014] Preferably, in S2: the above failure probability is calculated using Monte Carlo simulation, and the calculation formula is:

[0015] In the formula, This represents the slope failure probability. Let be the limit state function. This indicates that the slope is stable. This indicates slope instability; Let be the joint probability density function of random variables; the random variables include physical and mechanical parameters of soil and rock, geometric parameters of slope, groundwater occurrence conditions, and external load parameters. The global sensitivity analysis method described above is the Sobol method. The sensitivity indices include the first-order sensitivity index and the total sensitivity index, and their calculation formulas are as follows:

[0016]

[0017] In the formula, For the first The first-order sensitivity index corresponding to each input monitoring parameter; For the first The first-order variance contribution of each input monitoring parameter For the first One input monitoring parameter, The slope safety factor is calculated based on the dynamic risk assessment model; To fix the first When one monitoring parameter is taken, all other monitoring parameters The conditional mathematical expectation of the slope safety factor, taking all possible values. For the expected value of the above conditions with respect to the first... Calculate the variance of each monitoring parameter; The output variance of the slope safety factor; For the first The overall sensitivity index corresponding to each input monitoring parameter; For the first The total variance contribution of each input monitoring parameter For fixed removal All other monitoring parameters When determining the value of the slope safety factor, Regarding the first Monitoring parameters conditional variance; To calculate the expected value of the above conditional variance with respect to all other monitoring parameters.

[0018] By accurately calculating the failure probability through Monte Carlo simulation and combining it with the Sobol method to quantify the sensitivity of monitoring parameters, a quantitative basis is provided for the identification of target risk areas and key monitoring variables.

[0019] Preferably, in S3: the multi-objectives of the above-mentioned multi-objective optimization algorithm include maximizing the coverage of the target risk area and minimizing the investment of monitoring resources; the above-mentioned multi-objective optimization algorithm is at least one of non-dominated sorting genetic algorithm, multi-objective particle swarm optimization algorithm, multi-objective differential evolution algorithm and multi-objective simulated annealing algorithm.

[0020] By clarifying the core objectives of multi-objective optimization and selecting algorithms, we can ensure the coverage of target risk areas while achieving reasonable control of monitoring resource investment.

[0021] Preferably, the objective function for maximizing the coverage of the aforementioned target risk area is:

[0022] In the formula, Maximize the objective function value to cover high-risk areas; For risk unit serial number; The total number of units obtained after dividing the slope monitoring area according to a preset grid or geological unit; For the first The importance weight of each risk unit; To determine the first The indicator function for whether a risk unit is effectively covered by the monitoring point takes a value of 1 if effective coverage is determined, and a value of 0 otherwise. The objective function for minimizing the above monitoring resource input is:

[0023] In the formula, To minimize the objective function value for monitoring resource input; The candidate monitoring point number; The total number of candidate monitoring points; For the first Resource consumption coefficient of each monitoring point; To determine whether to deploy the first The decision variable for each monitoring point is set to 1 if deployment is confirmed, and 0 otherwise.

[0024] By quantifying the optimization direction through specific objective functions, the solution of multi-objective optimization algorithms becomes more targeted.

[0025] Preferably, in S3: when determining the location and density of monitoring points, the determination is also made in conjunction with a stage-adaptive rule base; the stage-adaptive rule base includes: Construction period rules: Monitoring points shall be prioritized for placement on the excavation face and key parts of the support structure, and the number of monitoring points per unit area shall be higher than the density of monitoring points in the corresponding area during the operation period; the above-mentioned excavation face refers to the slope area where excavation is currently underway during the current construction phase, and the above-mentioned key parts of the support structure refers to the main load-bearing components and component connection nodes specified in the slope support structure design documents. Operational rules: Monitoring points are set up on the slope stability base; the aforementioned stability base is the slope foundation area that has been confirmed by geological stability assessment to have no significant creep risk and whose structural integrity coefficient is greater than the preset threshold; Dynamic migration rules: Monitoring points deployed during the construction period will be retained if they do not affect the use during the operation period; if monitoring points deployed during the construction period need to be removed, the new deployment location will be the preset location of the monitoring points during the operation period.

[0026] By using phased adaptive rules, the layout of monitoring points is adapted to the different needs of the construction and operation phases, ensuring the targeted nature of monitoring during the construction phase and the continuity of data during the operation phase, thus achieving full-cycle monitoring.

[0027] Preferably, the above method further includes: When setting up monitoring points before construction, the potential disturbance areas during the construction period should be considered, and space for dynamic adjustment should be reserved. If the above-mentioned multi-source monitoring data shows abnormalities or exceeds the preset monitoring threshold during the construction period, or if supplementary geological exploration reveals new geological information, return to S1 to update the plan.

[0028] During the operation period, the system will periodically return to S1 to update the plan; when extreme weather occurs or monitoring data shows a trend change within a preset time period, the system will return to S1 to update the plan. By combining multi-source monitoring data within a preset period, the evolution pattern of slope performance is analyzed, and the monitoring points are adjusted accordingly. After each update of the above scheme, the multi-source monitoring data from the new monitoring points is returned to S1 for scheme self-checking and closed-loop feedback optimization.

[0029] By reserving space for dynamic adjustment, clarifying the triggering conditions for scheme updates, and establishing a closed-loop feedback mechanism, the monitoring network can achieve full-cycle adaptive optimization and respond promptly to changes in geological conditions and slope status.

[0030] In a second aspect, the present invention provides a slope monitoring point layout system for the entire construction and operation cycle. When the system is running, it executes the above-mentioned slope monitoring point layout method for the entire construction and operation cycle.

[0031] By systematically implementing the aforementioned methods, data processing, analysis and calculation, decision optimization, and feedback adjustment are integrated, thereby improving the feasibility of the methods in engineering applications and their implementation efficiency.

[0032] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention provides a method and system for the layout of slope monitoring points throughout the entire construction and operation cycle. By standardizing and integrating multi-source monitoring data, accurately identifying target risk areas and key monitoring variables, and using a multi-objective optimization algorithm to solve for the optimal layout scheme, the scientific and targeted layout of monitoring points is achieved. This adapts to the dynamic needs of the entire construction and operation cycle, avoids monitoring blind spots and resource waste, enables the full-cycle adaptive adjustment of the slope monitoring system, and improves the accuracy of stability assessment and the efficiency of resource allocation. Attached Figure Description

[0033] Figure 1 This is a schematic diagram of the slope monitoring point layout method for the entire construction and operation cycle in Example 1; Figure 2 This is a schematic diagram of the slope monitoring point layout system for the entire construction and operation cycle in Example 2. Detailed Implementation

[0034] The present invention will now be described in further detail with reference to specific embodiments. However, this should not be construed as limiting the scope of the present invention to the following embodiments; all technologies implemented based on the content of the present invention fall within the scope of the present invention.

[0035] Unless otherwise specified, the terms "upper," "lower," "left," "right," "center," "inner," and "outer," etc., used in the description of specific embodiments of the present invention to indicate orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings, or the orientation or positional relationship in which the product / equipment / device is usually placed during use. These terms are merely for the purpose of facilitating the description of the present invention or simplifying the description in specific embodiments, and for enabling those skilled in the art to quickly understand the solution, and do not indicate or imply that a particular device / component / element must have a specific orientation, or be constructed and operated in a specific positional relationship. Therefore, they should not be construed as limitations on the present invention.

[0036] Furthermore, the use of terms such as "horizontal," "vertical," "suspended," "parallel," and "coaxial" does not imply that the corresponding device / component / element must be absolutely horizontal, vertical, suspended, parallel, or coaxial. Slight tilt or deviation is permissible, as long as it does not affect the normal function of the relevant component. For example, "horizontal" simply means that its direction is more horizontal relative to "vertical," not that the structure must be perfectly horizontal; a slight tilt is acceptable. "Coaxial" means that two components are arranged as coaxially as possible, allowing them to move coaxially or approximately coaxially when their relative positions change. Alternatively, it can be simplified to mean that the corresponding device / component / element, when arranged in "horizontal," "vertical," "suspended," "parallel," or "coaxial" directions, can have an error / deviation of ±10% relative to the corresponding direction, more preferably within ±8%, more preferably within ±6%, more preferably within ±5%, and more preferably within ±4%. For example, the deviation in the "coaxial" direction is controlled within 0.2-1mm, preferably within 0.2-0.5mm. As long as the corresponding device / component / element is within the error / deviation range, it can still achieve its function in the solution of the present invention.

[0037] Furthermore, the use of terms such as "first," "second," and "third" in terminology is merely for distinguishing descriptions of identical or similar components and should not be interpreted as emphasizing or implying the relative importance of a particular component.

[0038] Furthermore, in the description of the embodiments of the present invention, "several", "more than", and "a number of" represent at least two. The number can be any number, such as two, three, four, five, six, seven, eight, or nine, and can even exceed nine.

[0039] Furthermore, in the description of the technical solution of this invention, unless otherwise explicitly specified / limited / restricted, the terms "set up," "install," "connect," "link," "provided with," "laid out," and "arranged" should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to connection methods commonly used in the art, such as welding, riveting, bolting, and threaded connections. Such connections can be mechanical, electrical, or communication connections; they can be direct connections or indirect connections through an intermediate medium; and they can refer to the internal communication between two components.

[0040] Example 1 This embodiment uses a steep highway slope as an application scenario to illustrate the method of the present invention. The method specifically includes the following steps, and the method flow is as follows: Figure 1 As shown: S1. Multi-source data acquisition and unified data warehouse construction: Multi-source monitoring data for the slope was acquired. The basic static data included: GIS three-dimensional terrain model data (DEM data) of the slope area, physical and mechanical parameters of the soil and rock mass (cohesion c, internal friction angle φ, unit weight γ), geological structure distribution data, slope geometric design drawings, support structure design drawings, and historical landslide disaster data of the area in recent years. The dynamic updated data included: staged excavation process plan, support structure construction progress, blasting operation plan, slope surface displacement data collected by GNSS receiver, deep displacement data collected by inclinometer, soil and rock stress data collected by stress and strain sensor, groundwater seepage pressure data collected by piezometer, and regional rainfall data collected by rain gauge.

[0041] The above data was processed as follows: outliers in the displacement data were removed using the 3σ criterion; CAD format design drawings, BIM support models, and GIS topographic data were converted to IFC standard format; spatial registration was achieved by converting the WGS84 coordinate system to the engineering independent coordinate system, and time registration was achieved by aligning the time scale; and a unified data warehouse was constructed using an ontology-based data fusion method.

[0042] In addition to ontology-based data fusion methods, the following data fusion methods can also be used as needed: XML-based data fusion: simple to implement, but poor scalability; RDF-based data fusion: supports semantic reasoning, but is complex to implement; Knowledge graph-based data fusion supports complex semantic relationships, but its construction and maintenance costs are high.

[0043] S2. Dynamic Risk Assessment and Sensitivity Analysis: Based on a unified data warehouse, a dynamic risk assessment model coupled with the limit equilibrium method and the finite element method is adopted. Inputting physical and mechanical parameters of soil and rock, slope geometric parameters, groundwater occurrence conditions and external load parameters (such as construction disturbance load, seismic load, rainfall load, etc.), the failure probability of different areas of the slope is calculated through Monte Carlo simulation, and the distribution area of ​​weak interlayers and the toe of the slope are identified as target risk areas.

[0044] The dynamic risk assessment model can also be replaced with the following other solutions according to actual needs: Reliability index method: High computational efficiency, suitable for small to medium scale problems, but relatively low accuracy; Response surface methodology: It approximates the true response by constructing a response surface function, which is computationally efficient, but its accuracy depends on the fitting accuracy of the response surface function. Support Vector Machine: It builds risk prediction models using machine learning methods, is suitable for large-scale data, but requires a large number of training samples; The Sobol method was used to calculate the sensitivity index of each monitoring parameter to the slope safety factor, and to determine whether each monitoring parameter was a key monitoring variable.

[0045] The Sobol method can also be replaced by the following other solutions depending on actual needs: Morris method: High computational efficiency, suitable for parameter screening, but can only provide qualitative analysis; FAST method: High computational efficiency, suitable for large-scale problems, but can only calculate the first-order sensitivity index; Local sensitivity analysis: It is simple to calculate, but it can only analyze the influence of a single parameter and cannot consider the interaction between parameters.

[0046] S3. Multi-objective optimization to determine the monitoring point layout scheme: With the objectives of maximizing coverage of the target risk area and minimizing monitoring resource input, a non-dominated sorting genetic algorithm is used to solve for the Pareto optimal solution set. Risk units are divided into grids of a certain size, and importance weights are assigned to high-risk and ordinary areas. Resource consumption coefficients include sensor resource consumption and annual maintenance resource consumption, and decision variables are determined based on the optimization results.

[0047] The non-dominated sorting genetic algorithm can also be replaced by the following algorithms according to actual needs: Multi-objective particle swarm optimization algorithm: fast convergence speed, suitable for large-scale optimization problems, but prone to getting trapped in local optima; Multi-objective differential evolution algorithm: has few parameters and is simple to implement, but has a slow convergence speed; Multi-objective simulated annealing algorithm: strong global search capability, but large computational cost and slow convergence speed.

[0048] Based on the phased adaptive rule base: during the construction period, monitoring points are prioritized to be placed on the excavation face and key parts of the support structure, with high point density, and temporary sensors are allowed; during the operation period, monitoring points focus on the overall stability of the slope, and the monitoring points are placed on stable bases, with sensors emphasizing permanence and data continuity; when temporary monitoring points during the construction period need to be removed, the new placement location overlaps with the monitoring points during the operation period to ensure data comparability.

[0049] Dynamic adjustment and closed-loop feedback optimization: Initial deployment before construction: Based on detailed geological surveys and GIS models, an initial monitoring network design is conducted using optimization algorithms, focusing on covering known weak interlayers, potential sliding surfaces, and the areas surrounding important structures. The initial deployment plan must consider potential disturbance areas during construction and allow for dynamic adjustments.

[0050] Dynamic adjustments during construction: Dynamic adjustments are triggered before / after the start of major construction procedures (such as staged excavation and blasting), when monitoring data shows abnormalities or exceeds thresholds, or when supplementary geological surveys reveal new geological information. A new risk assessment is conducted based on the latest slope geometry, stress field changes, and monitoring feedback. For example, when excavating to a new slope toe, it is recommended to add inclinometers and stress gauges at the slope toe and potential slip surface exit area.

[0051] Dynamic optimization during operation: Optimization is triggered by regular (e.g., quarterly / annual) assessments, after extreme weather events (e.g., heavy rain), and when monitoring data shows long-term trend changes. Long-term monitoring data is used to analyze the evolution of slope performance. For areas with good stability, the monitoring frequency can be appropriately reduced or the monitoring points adjusted; for areas showing creep trends, the monitoring density can be increased or the types of monitoring points can be expanded. Machine learning models are used to predict potential future risk areas, allowing for proactive monitoring point deployment.

[0052] Closed-loop feedback: The original multi-source monitoring data is updated using monitoring data from the newly deployed points, and the above process is repeated to verify the effectiveness of the deployment plan. If new abnormal areas are found or existing points fail, a new round of analysis and decision-making is triggered to achieve continuous improvement.

[0053] Based on the above method, the present invention avoids the problem of waste or insufficiency of monitoring resources that may occur in traditional experience-based deployment. It can save monitoring resources to the greatest extent while ensuring monitoring effectiveness. It is expected to reduce the resource consumption of the monitoring system by more than 15%. Moreover, it can effectively cope with the uncertainty of geological conditions during construction and the long-term changes in the operating environment, making the monitoring system more robust and adaptable.

[0054] Example 2 This embodiment describes the system of the present invention, which can be divided into four layers, as shown in the following figure. Figure 2 As shown, the details are as follows: (1) Data layer: Integrates multi-source data, including GIS 3D model (DEM data), geological survey report, design drawings, construction schedule, real-time monitoring data (displacement, stress, hydrology, etc.), meteorological data, and historical disaster data. A unified data warehouse is established through data cleaning, format conversion, and spatiotemporal registration.

[0055] (2) Analysis layer: including dynamic risk assessment module and sensitivity analysis module. The dynamic risk model assessment module combines geological conditions, construction activities and real-time monitoring data to calculate the risk level and failure probability of different areas of the slope through Monte Carlo simulation and identify target risk areas; the sensitivity analysis module has a built-in Sobol method to calculate the first-order sensitivity index Si and the total sensitivity index STi of each monitoring parameter, analyze the degree of influence of different monitoring parameters on the overall slope stability assessment results, identify key monitoring variables, and also supports alternative schemes such as Morris screening method and FAST method.

[0056] (3) Decision layer: including a multi-objective optimization module and a stage-adaptive rule base. The multi-objective optimization module has a built-in non-dominated sorting genetic algorithm to solve the Pareto optimal solution set according to the objective function, and also supports alternative schemes such as multi-objective particle swarm optimization algorithm; the stage-adaptive rule base stores the construction period, operation period and dynamic migration rules, and constrains the optimization results.

[0057] (4) Execution feedback layer: Generate dynamic layout schemes and visualize them based on the BIM / GIS platform. At the same time, verify the effectiveness of the schemes based on the monitoring data of the newly deployed points, trigger a new round of analysis and decision-making, and form a closed-loop optimization.

[0058] When the system is running, the following process occurs: Initial Layout (Pre-Construction): Based on detailed geological surveys and GIS models, an initial monitoring network design is conducted using optimization algorithms, focusing on covering known weak interlayers, potential sliding surfaces, and the areas surrounding important structures. The initial layout plan must consider potential disturbance areas during construction and allow for dynamic adjustments.

[0059] Dynamic adjustments during construction: Dynamic adjustments are triggered before / after the start of major construction procedures (such as staged excavation and blasting), when monitoring data shows abnormalities or exceeds thresholds, or when supplementary geological surveys reveal new geological information. The system reassesses the risk based on the latest slope geometry, stress field changes, and monitoring feedback. For example, when excavating to a new slope toe, the system may recommend adding inclinometers and stress gauges at the slope toe and the potential slip surface exit area.

[0060] Dynamic optimization during operation: Optimization is triggered by regular (e.g., quarterly / annual) assessments, after extreme weather events (e.g., heavy rain), and when monitoring data shows long-term trend changes. Long-term monitoring data is used to analyze the evolution of slope performance. For areas with good stability, the monitoring frequency can be appropriately reduced or the monitoring points adjusted; for areas showing creep trends, the monitoring density can be increased or the types of monitoring points can be expanded. Machine learning models are used to predict potential future risk areas, allowing for proactive monitoring point deployment.

[0061] Closed-loop feedback optimization: Monitoring data from newly deployed points is fed back to the system to verify the effectiveness of the deployment plan. If new abnormal areas are discovered or existing points fail, a new round of analysis and decision-making is triggered to achieve continuous improvement.

[0062] After the system starts up, the data layer collects and processes multi-source monitoring data to build a unified data warehouse; The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for arranging slope monitoring points throughout the entire construction and operation cycle, characterized in that, The method includes the following steps: S1. Acquire multi-source monitoring data of the slope, perform data cleaning, format conversion and spatiotemporal registration processing on the multi-source data, and build a unified data warehouse; S2. Based on the unified data warehouse, a dynamic risk assessment model coupled with the limit equilibrium method and the finite element method is used to calculate the failure probability of different areas of the slope and identify the target risk area; a global sensitivity analysis method is used to calculate the sensitivity index of each monitoring parameter in the unified data warehouse to the slope safety factor and identify key monitoring variables. S3. Based on the target risk area and the key monitoring variables, a multi-objective optimization algorithm is used to solve for the Pareto optimal solution set, and the location and density of monitoring points are determined.

2. The slope monitoring point layout method for the entire construction and operation cycle as described in claim 1, characterized in that, The multi-source monitoring data includes basic static data and dynamically updated data; The basic static data includes GIS 3D terrain model data of the slope area, slope engineering geological survey data, slope engineering design documents, and historical slope disaster data of the slope area; the slope engineering geological survey data includes at least one of the following: physical and mechanical parameters of soil and rock mass, geological structure distribution data, and detection data of weak interlayers and potential sliding surfaces; the slope engineering design documents include at least one of the following: slope geometry design drawing, support structure design drawing, and preliminary monitoring layout plan drawing; the historical slope disaster data includes at least one of the following: occurrence time, location, scale, and triggering factors of landslides and collapses. The dynamically updated data includes slope construction progress data and real-time monitoring data of the slope body and surrounding environment; the construction progress data includes at least one of the following: graded excavation process plan, support structure construction progress, and blasting operation plan; the real-time monitoring data of the slope body and surrounding environment includes at least one of the following: slope displacement data, rock and soil stress and strain data, slope and surrounding hydrological data, and environmental meteorological data.

3. The slope monitoring point layout method for the entire construction and operation cycle as described in claim 1, characterized in that, In S1: Data cleaning of the multi-source data is performed using 3... The criteria or box plot method are used to remove outlier data points and noisy data; the format conversion converts the multi-source monitoring data into the IFC standard format; the spatiotemporal registration adopts geodetic coordinate system transformation technology and time scale alignment technology; when constructing a unified data warehouse, the data fusion method used is at least one of ontology-based data fusion method, XML-based data fusion method, RDF-based semantic data fusion method, and knowledge graph-based association data fusion method.

4. The slope monitoring point layout method for the entire construction and operation cycle as described in claim 1, characterized in that, In S2: the dynamic risk assessment model can be replaced by at least one of the reliability index method, response surface method, and support vector machine risk prediction model; the global sensitivity analysis method can be replaced by at least one of the Morris screening method, FAST method, and local sensitivity analysis method.

5. The slope monitoring point layout method for the entire construction and operation cycle according to claim 1, characterized in that, In S2: The failure probability is calculated using Monte Carlo simulation, and the calculation formula is as follows: In the formula, This represents the slope failure probability. It is the limit state function; Let be the joint probability density function of random variables; the random variables include physical and mechanical parameters of soil and rock mass, geometric parameters of slope, groundwater occurrence conditions, and external load parameters. The global sensitivity analysis method is the Sobol method, and the sensitivity index includes the first-order sensitivity index and the total sensitivity index, calculated using the following formulas: In the formula, For the first The first-order sensitivity index corresponding to each input monitoring parameter; For the first The first-order variance contribution of each input monitoring parameter For the first One input monitoring parameter, The slope safety factor is calculated based on the dynamic risk assessment model; To fix the first When one monitoring parameter is taken, all other monitoring parameters The conditional mathematical expectation of the slope safety factor, taking all possible values. For the expected value of the above conditions with respect to the first... Calculate the variance of each monitoring parameter; The output variance of the slope safety factor; For the first The overall sensitivity index corresponding to each input monitoring parameter; For the first The total variance contribution of each input monitoring parameter For fixed removal All other monitoring parameters When determining the value of the slope safety factor, Regarding the first Monitoring parameters conditional variance; To calculate the expected value of the above conditional variance with respect to all other monitoring parameters.

6. The slope monitoring point layout method for the entire construction and operation cycle according to claim 1, characterized in that, In S3: the multi-objective optimization algorithm includes maximizing the coverage of the target risk area and minimizing the investment of monitoring resources; the multi-objective optimization algorithm is at least one of the following: non-dominated sorting genetic algorithm, multi-objective particle swarm optimization algorithm, multi-objective differential evolution algorithm and multi-objective simulated annealing algorithm.

7. The slope monitoring point layout method for the entire construction and operation cycle as described in claim 6, characterized in that, The objective function for maximizing the coverage of the target risk area is: In the formula, Maximize the objective function value to cover high-risk areas; For risk unit serial number; The total number of units obtained after dividing the slope monitoring area according to a preset grid or geological unit; For the first The importance weight of each risk unit; To determine the first The indicator function for whether a risk unit is effectively covered by the monitoring point takes a value of 1 if effective coverage is determined, and a value of 0 otherwise. The objective function for minimizing the input of monitoring resources is: In the formula, To minimize the objective function value for monitoring resource input; The candidate monitoring point number; The total number of candidate monitoring points; For the first Resource consumption coefficient of each monitoring point; To determine whether to deploy the first Decision variables for each monitoring point.

8. The slope monitoring point layout method for the entire construction and operation cycle according to claim 1, characterized in that, In S3: When determining the location and density of monitoring points, a stage-adaptive rule base is also used; the stage-adaptive rule base includes: Construction period rules: Monitoring points shall be prioritized for placement on the excavation face and key parts of the support structure, and the number of monitoring points per unit area shall be higher than the density of monitoring points in the corresponding area during the operation period; the excavation face refers to the slope area where excavation is currently underway during the current construction phase, and the key parts of the support structure refer to the main load-bearing components and component connection nodes specified in the slope support structure design documents. Operational rules: Monitoring points are set up on the slope stability base; the stability base is the slope foundation area that has been confirmed by geological stability assessment to have no significant creep risk and whose structural integrity coefficient is greater than a preset threshold; Dynamic migration rules: Monitoring points deployed during the construction period will be retained if they do not affect the use during the operation period; if monitoring points deployed during the construction period need to be removed, the new deployment location will be the preset location of the monitoring points during the operation period. After determining the location and density of the monitoring points, a slope monitoring point layout plan is generated and visualized.

9. The slope monitoring point layout method for the entire construction and operation cycle according to claim 1, characterized in that, The method further includes: When setting up monitoring points before construction, the potential disturbance areas during the construction period should be considered, and space for dynamic adjustment should be reserved. If the multi-source monitoring data during the construction period shows abnormalities or exceeds the preset monitoring threshold, or if supplementary geological exploration reveals new geological information, return to S1 to update the scheme. During the operation period, the system will periodically return to S1 to update the plan; when extreme weather occurs or monitoring data shows a trend change within a preset time period, the system will return to S1 to update the plan. By combining multi-source monitoring data within a preset period, the evolution pattern of slope performance is analyzed, and the monitoring points are adjusted accordingly. After each update of the scheme, the scheme is self-checked by returning multi-source monitoring data from the new monitoring points to S1, and closed-loop feedback optimization is performed.

10. A slope monitoring point layout system covering the entire construction and operation cycle, characterized in that, When the system is running, it executes the slope monitoring point layout method as described in any one of claims 1 to 9, which is applicable to the entire construction and operation cycle.

Images