Water conservancy project construction progress dynamic correction system based on time sequence analysis

Abstract

The invention relates to the technical field of construction progress optimization, in particular to a water conservancy project construction progress dynamic correction system based on time sequence analysis, which obtains point cloud data of a construction excavation surface through three-dimensional point cloud scanning equipment, identifies and extracts structural feature information of the excavation surface, generates a structural mechanical model, and obtains the construction progress dynamic correction system based on the structural mechanical model. And in combination with material strength evolution data in the reinforcing material, multi-target optimization is carried out on the supporting scheme and the operation time sequence, and a dynamic operation instruction is output. Based on a composite structure model comprising a real rock mass structure and a real strength reinforcing system, performing rehearsal calculation on construction operation in the dynamic operation instruction to obtain the minimum safety margin of the composite structure, and when the minimum safety margin is higher than a preset threshold value, outputting a construction authorization signal, and when the minimum safety margin is lower than a preset threshold value, a construction forbidding signal is output, and supplementary reinforcement is triggered. Therefore, the active intervention capability in the construction risk is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of construction progress optimization, and in particular to a dynamic correction system for water conservancy project construction progress based on time series analysis. Background Art

[0002] Project management systems are often used to manage the construction progress of large-scale engineering projects. Based on a work breakdown structure and utilizing classic project management concepts such as the critical path method, program review and evaluation techniques, or Gantt charts, they plan, schedule, and allocate resources for each phase of the construction process. Based on pre-defined task dependencies, durations, and required resources, a global construction schedule is generated. Some systems also integrate resource management, cost control, and risk registration modules, allowing for manual updating of task status, recording of actual expenditures, and tracking of identified risks during plan execution.

[0003] However, these conventional project management systems have significant limitations when handling highly uncertain and dynamic projects, such as slope reinforcement for mountain reservoir dams. The progress of slope reinforcement construction in water conservancy projects is not only constrained by the conventional supply of personnel, equipment, and materials, but is also heavily dependent on complex and dynamically changing on-site natural conditions, such as real-time slope displacement data, groundwater level fluctuations, and unexpected severe weather events. While existing systems can adjust plans, these adjustments typically require managers to rely on personal experience to reassess the impact upon discovery, manually modify system parameters, and then recalculate. This process is inefficient and fails to meet the demands of real-time decision-making. The system also lacks a dynamic correction mechanism based on time-series data analysis, unable to automatically and continuously integrate dynamic information streams such as monitoring data from on-site sensors and weather forecasts. It also fails to predict potential schedule deviations and proactively generate correction plans based on this real-time data. Consequently, existing technologies cannot effectively address the management challenges of frequently invalidated construction plans due to dynamic changes in the external environment.

[0004] Therefore, a dynamic correction system for water conservancy project construction progress based on time series analysis is proposed. Summary of the Invention

[0005] The purpose of the present invention is to provide a dynamic correction system for the construction progress of a water conservancy project based on time series analysis. The system obtains point cloud data of the construction excavation surface through a three-dimensional point cloud scanning device, identifies and extracts structural feature information of the excavation surface, and generates a structural mechanics model. Based on the structural mechanics model, combined with the material strength evolution data in the reinforcement material, a multi-objective optimization is performed on the support scheme and the operation sequence, and dynamic operation instructions are output. Based on a composite structure model including a real rock structure and a real strength reinforcement system, the construction operations in the dynamic operation instructions are pre-calculated to obtain the minimum safety margin of the composite structure. When the minimum safety margin is higher than a preset threshold, a construction authorization signal is output. When the minimum safety margin is lower than the preset threshold, a construction prohibition signal is output and supplementary reinforcement is triggered. This improves the ability to actively intervene in construction risks.

[0006] To achieve the above object, the present invention provides the following technical solutions: A dynamic correction system for water conservancy project construction progress based on time series analysis, comprising: A synchronous modeling module is used to obtain point cloud data of the construction excavation surface through 3D point cloud scanning equipment, and use a pre-trained convolutional neural network model to identify and extract structural feature information of the excavation surface to generate a structural mechanics model; A reinforcement optimization module is used to perform multi-objective optimization of support schemes and operation sequences based on the structural mechanics model and combined with the material strength evolution data of the reinforcement materials, and output dynamic operation instructions; The safety decision module is used to perform pre-calculations on the construction operations in the dynamic operation instructions based on a composite structure model including a real rock structure and a real strength reinforcement system, and obtain the minimum safety margin of the composite structure. When the minimum safety margin is higher than a preset threshold, a construction authorization signal is output; when the minimum safety margin is lower than the preset threshold, a construction prohibition signal is output and supplementary reinforcement is triggered.

[0007] Preferably, the structural mechanics model includes a geometry layer, a physical property layer and a boundary condition layer; The geometric layer uses an adaptive mesh simplification method to convert the structural surface attitude angle, trace length, and opening width data in the 3D point cloud data into simplified 3D geometric unit node coordinates and unit connection relationships, generating simplified discretized geometric units containing the main control joint surface and fracture surface; The physical attribute layer uses a partition assignment method to assign the rock mass elastic modulus, Poisson's ratio, internal friction angle, cohesion data obtained from geological surveys, as well as the friction coefficient, normal stiffness, and tangential stiffness data of the structural surface to geometric units according to engineering partitions, and sets the parameter uncertainty range to form a structural mechanics model; The boundary condition layer uses a load grading algorithm to convert excavation unloading, ground stress, groundwater pressure, and construction load data into node force and displacement constraints of three-dimensional geometric unit nodes in stages. The geometric layer data provides the spatial positioning basis for the physical property layer, and the physical property layer data provides material response parameters for the boundary condition layer.

[0008] Preferably, the material strength evolution data is obtained in the following manner: Obtain sensor data from the anchor grouting material, use the modified hydration reaction kinetics model, input the collected sensor data into the maturity theory to obtain hydration data; By establishing an empirical strength-hydration relationship model, the hydration data are converted into time-varying trend data of compressive strength, tensile strength, and elastic modulus, generating a material strength evolution trend curve with time as the horizontal axis and strength parameter as the vertical axis.

[0009] Preferably, the dynamic job instruction acquisition method is: The structural mechanics model and material strength evolution data are input into a multi-objective genetic algorithm optimization engine, and the safety factor is set as the main constraint, and the construction cost and construction period are set as secondary optimization objectives; the optimization variables include the discrete range of anchor rod length, the discrete range of anchor rod spacing, the limited type of grouting material, and the thickness classification of shotcrete; the strong constraints include the minimum safety factor being greater than the value required by the specification and the material strength meeting the requirements of the design specification; through the weighted Pareto optimal solution screening method, the top three alternative solutions with the best comprehensive evaluation are selected from the constrained feasible solution set, and dynamic operation instructions containing the construction process number, strength compliance triggering condition, construction parameter range, and completion judgment standard are output.

[0010] Preferably, the composite structure model includes a rock mass sub-model, a support sub-model and an interaction interface model, specifically: The rock mass sub-model is based on the data in the geometric units and physical property layers of the structural mechanics model, and uses the elastic-plastic constitutive relationship and joint surface slip model to describe the mechanical behavior of the main rock mass and structural surfaces; The support sub-model uses simplified beam elements to simulate anchor bolts and simplified shell elements to simulate shotcrete based on the time-varying trend data in the material strength evolution data, thus obtaining the staged mechanical behavior of the support system. The interaction interface model uses a linear contact algorithm to process the contact force transmission between the rock mass and the support. Through deformation coordination conditions and static equilibrium conditions, a composite structure model of the rock mass and support is formed. The rock mass sub-model data provides boundary conditions for the interaction interface, and the support sub-model data provides constraint parameters for the interaction interface.

[0011] Preferably, the minimum safety margin is obtained as: Apply the load disturbance of the next excavation to the composite structure model and conduct structural response analysis. During the calculation process, monitor the stress state of key units and nodes to determine the dangerous state of rock mass units and support units. The dangerous state determination process is as follows: calculate the safety factor of key units and nodes, which is defined as the ratio of the failure strength to the actual stress, select the minimum value of the safety factor of the important control section unit as the minimum safety margin of the composite structure, and record the unit position and failure mode corresponding to the minimum safety margin.

[0012] Preferably, the specific process of triggering the supplementary reinforcement is: When the minimum safety margin is lower than the preset threshold, the unit position corresponding to the minimum safety margin is located and an early warning message is sent; Based on the failure mode, corresponding reinforcement alternatives are recommended from a preset library of standardized reinforcement measures, including the recommended location coordinates and technical parameter ranges for adding anchor rods, the recommended area range and thickness parameter range for adding shotcrete, and the recommended length and tension parameter range for setting prestressed anchor cables; The selected reinforcement scheme data is fed back to the reinforcement optimization module for re-optimization calculation, dynamic operation instructions are updated, and the preview calculation is repeated until the result meets the minimum safety margin greater than the preset threshold.

[0013] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention obtains point cloud data of the construction excavation surface by introducing three-dimensional point cloud scanning technology, intelligently extracts structural feature information, and assembles it into a digital structural mechanics model. It effectively improves the true restoration of the structural model of the construction site. At the same time, the structural mechanics model includes a geometric layer, a physical property layer, and a boundary condition layer; the geometric layer uses an adaptive grid simplification method to simplify the structural surface of the point cloud, the physical property layer assigns regional geological parameters to the nodes and introduces a parameter uncertainty management mechanism, and the boundary condition layer dynamically applies constrained mechanical conditions through a load grading algorithm to ensure the model's responsiveness and accuracy to changes in working conditions at different stages. Accurately simulating the mechanical evolution process of the construction site effectively improves the adaptability and feasibility of the project.

[0014] 2. This invention utilizes a reinforcement optimization module to establish a multi-objective optimization mechanism based on material strength evolution data. This mechanism couples support scheme development with the time-varying strength behavior of construction materials, creating a dynamic work instruction based on "strength trigger conditions + construction process number." Unlike rigid scheduling mechanisms based on empirical parameter construction, this method dynamically adjusts work content based on real-time construction progress and material properties, improving the efficiency of construction resource allocation and the flexibility of construction response.

[0015] 3. This invention establishes a closed-loop mechanism for construction safety evaluation and response through a dynamic safety assurance system of "composite structure model + minimum safety margin analysis + reinforcement strategy recommendation." Structural mechanics simulations are performed on the rock mass, support, and interaction interfaces. Using deformation coordination and contact force transfer modeling methods, the stress response of the composite structure is dynamically calculated after simulating the next excavation load disturbance, and the minimum safety factor of key units is extracted as a safety margin indicator. This achieves high-frequency, real-time, model-driven safety prediction and reinforcement scheduling, improving the system's proactive intervention capabilities and decision-making intelligence in the face of sudden construction risks, thereby enhancing the stability of the entire water conservancy project construction phase. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of the structure of a dynamic correction system for water conservancy project construction progress based on time series analysis provided by the present invention; Figure 2 A schematic diagram of a process flow for dynamic correction of water conservancy project construction progress based on time series analysis provided by the present invention; Figure 3 A schematic diagram of the dynamic correction process of the construction progress provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0018] Example 1:

[0019] The present invention provides a dynamic correction system for water conservancy project construction progress based on time series analysis, the framework structure of which refers to Figure 1 A structural diagram of a dynamic correction system for water conservancy project construction progress based on time series analysis. For the specific implementation process, refer to Figure 2 , the details are as follows: A synchronous modeling module is used to obtain point cloud data of the construction excavation surface through a 3D point cloud scanning device, and use a pre-trained convolutional neural network model to identify and extract structural feature information of the excavation surface, and assemble the structural feature information into the digital mechanical model to generate a structural mechanical model; The structural mechanics model includes a geometry layer, a physical property layer and a boundary condition layer; The geometric layer uses an adaptive mesh simplification method to convert the structural surface attitude angle, trace length, and opening width data in the 3D point cloud data into simplified 3D geometric unit node coordinates and unit connection relationships, generating simplified discretized geometric units containing the main control joint surface and fracture surface; The physical attribute layer uses a partition assignment method to assign the rock mass elastic modulus, Poisson's ratio, internal friction angle, cohesion data obtained from geological surveys, as well as the friction coefficient, normal stiffness, and tangential stiffness data of the structural surface to geometric units according to engineering partitions, and sets the parameter uncertainty range to form a structural mechanics model; The boundary condition layer uses a load grading algorithm to convert excavation unloading, ground stress, groundwater pressure, and construction load data into node force and displacement constraints of three-dimensional geometric unit nodes in stages. The geometric layer data provides the spatial positioning basis for the physical property layer, and the physical property layer data provides material response parameters for the boundary condition layer.

[0020] In this embodiment, a synchronous modeling module, utilizing a three-dimensional point cloud scanning device and a convolutional neural network model, enables real-time and accurate acquisition of structural feature information of the construction excavation surface. This information is then efficiently assembled into a digital mechanical model to generate a homogeneous structural mechanical model, significantly improving model accuracy and reliability. The geometry layer employs an adaptive mesh simplification method to effectively reduce computational effort and improve efficiency. The physical property layer utilizes a partitioning and assignment method to fully account for the uncertainty of geological conditions and enhance model accuracy. The boundary condition layer utilizes a graded load application algorithm to realistically simulate construction load variations and improve model applicability. This solution provides a scientific basis for engineering design and construction, and offers the advantages of efficiency, precision, and reliability.

[0021] A reinforcement optimization module is used to perform multi-objective optimization of support schemes and operation sequences based on the structural mechanics model and combined with the material strength evolution data of the reinforcement materials, and output dynamic operation instructions; The material strength evolution data is obtained in the following manner: Acquire sensor data from the anchor grouting material and, using a modified hydration reaction kinetics model, input the collected sensor data into maturity theory to obtain hydration data. The sensors include wireless temperature sensors, humidity sensors, and resistivity sensors. The sensor sampling frequency is once every three hours, and a regular calibration mechanism is set up. The modified hydration reaction kinetic model includes an environment correction layer, a reaction rate calculation layer, and a hydration degree prediction layer: The environmental correction layer compares and analyzes the measured temperature, humidity, and environmental pressure data collected by the sensor with the benchmark parameters under standard curing conditions, and uses the temperature correction coefficient calculation formula and the humidity influence factor calculation formula to generate an environmental correction parameter group containing the temperature correction coefficient, humidity correction coefficient, and pressure correction coefficient. The environmental correction parameter group is used to correct the theoretical hydration reaction rate; The reaction rate calculation layer uses the environmental correction parameter group, material composition data, water-cement ratio data, and admixture type data as input variables to calculate the actual hydration reaction rate curve and cumulative hydration reaction degree curve considering the impact of the on-site environment; The hydration prediction layer uses an integral calculation method to numerically integrate the actual hydration reaction rate curve by time step. Combined with the cement clinker mineral composition data and the patterns of hydration product formation, this layer generates a hydration evolution curve with time as the independent variable, obtaining hydration data. This hydration evolution curve data provides the core input parameter for the empirical strength-hydration relationship model.

[0022] By establishing an empirical strength-hydration relationship model, the hydration data are converted into time-varying trend data of compressive strength, tensile strength, and elastic modulus, and a material strength evolution trend curve is generated with time as the horizontal axis and strength parameter as the vertical axis.

[0023] The strength-hydration empirical relationship model includes a strength prediction layer, a parameter correction layer, and a reliability assessment layer: The strength prediction layer inputs the hydration evolution curve data, material grade data, and mix design data into the strength development database. Using the strength-hydration relationship function and multiple regression analysis method, it calculates the theoretical prediction values ​​of the time-varying curves of compressive strength, tensile strength, and elastic modulus. The parameter correction layer is based on on-site sampling test data. It performs error analysis on the measured material strength data and the theoretical prediction value, calculates the compressive strength correction factor, tensile strength correction factor, and elastic modulus correction factor, and applies the correction factors to the theoretical prediction value to generate a corrected material strength evolution trend curve. The reliability assessment layer uses statistical analysis methods to compare and analyze historical inspection data, similar engineering data, and standard test data, and calculates the upper limit value, lower limit value, and confidence index for each strength parameter. The material strength evolution trend curve and reliability index data provide material parameter input and uncertainty quantification basis for the reinforcement optimization module.

[0024] In this embodiment, the temperature, humidity, and resistivity data of the anchor grouting material are collected in real time by sensors, and the modified hydration reaction kinetics model is used to generate a hydration degree evolution curve, which is converted into a time-varying trend of material strength to provide accurate input for reinforcement optimization. The environmental correction layer takes into account the influence of on-site temperature, humidity, and pressure to improve the adaptability of the model and the accuracy of prediction. The reinforcement optimization module combines strength data to perform multi-objective optimization, outputs dynamic operation instructions, and optimizes the support scheme. The strength-hydration degree model ensures reliable predictions through parameter correction and reliability evaluation. High-frequency sampling and regular calibration of sensors support intelligent management. This improves the level of dynamic optimization of support and enhances engineering safety.

[0025] The dynamic job instruction acquisition method is: The structural mechanics model and material strength evolution data are input into a multi-objective genetic algorithm optimization engine, and the safety factor is set as the main constraint, and the construction cost and construction period are set as secondary optimization objectives; the optimization variables include the discrete range of anchor rod length, the discrete range of anchor rod spacing, the limited type of grouting material, and the thickness classification of shotcrete; the strong constraints include the minimum safety factor being greater than the value required by the specification and the material strength meeting the requirements of the design specification; through the weighted Pareto optimal solution screening method, the top three alternative solutions with the best comprehensive evaluation are selected from the constrained feasible solution set, and dynamic operation instructions containing the construction process number, strength compliance triggering condition, construction parameter range, and completion judgment standard are output.

[0026] The multi-objective genetic algorithm optimization engine includes a population initialization layer, a fitness evaluation layer, and an evolutionary operation layer: The population initialization layer uses the anchor length discrete range data, anchor spacing discrete range data, grouting material type data, and shotcrete thickness classification data as the gene coding space to generate initial population individuals containing anchor length genes, spacing genes, material type genes, and thickness genes; The fitness evaluation layer takes structural mechanics model data, material strength evolution data, engineering cost database, and construction period quota data as input. Through the safety factor calculation algorithm, cost estimation algorithm, and construction period prediction algorithm, it calculates the safety factor evaluation value, construction cost evaluation value, and construction period evaluation value for each population individual, and uses the constraint violation calculation method to handle strong constraints. The evolutionary operation layer performs Pareto stratification on the fitness evaluation results through a non-dominated sorting algorithm and a crowding distance calculation algorithm, and uses a tournament selection method, a single-point crossover operation, and a uniform mutation operation to generate a new generation of populations. The output data of the evolutionary operation layer is a Pareto optimal solution set that has undergone multi-generation evolutionary optimization.

[0027] In this example, a multi-objective genetic algorithm was used to optimize construction parameters, with safety factors as the primary constraint, while minimizing both cost and construction schedule. By integrating structural mechanics models and material strength evolution data, dynamic work instructions were generated, improving construction accuracy and efficiency. Advanced evolutionary technology ensures a diverse and high-quality solution set, providing flexibility for decision-making.

[0028] The safety decision module is used to perform pre-calculations on the construction operations in the dynamic operation instructions based on a composite structure model including a real rock structure and a real strength reinforcement system, and obtain the minimum safety margin of the composite structure. When the minimum safety margin is higher than a preset threshold, a construction authorization signal is output; when the minimum safety margin is lower than the preset threshold, a construction prohibition signal is output and supplementary reinforcement is triggered.

[0029] The composite structure model includes a rock mass sub-model, a support sub-model and an interaction interface model, specifically: The rock mass sub-model is based on the data in the geometric units and physical property layers of the structural mechanics model, and uses the elastic-plastic constitutive relationship and joint surface slip model to deal with the mechanical behavior of the main rock mass and structural surfaces; The support sub-model uses simplified beam elements to simulate anchor bolts and simplified shell elements to simulate shotcrete based on the time-varying trend data in the material strength evolution data, thus obtaining the staged mechanical behavior of the support system. The interaction interface model uses a linear contact algorithm to process the contact force transmission between the rock mass and the support. Through deformation coordination conditions and static equilibrium conditions, a composite structure model of the rock mass and support is formed. The rock mass sub-model data provides boundary conditions for the interaction interface, and the support sub-model data provides constraint parameters for the interaction interface.

[0030] The joint surface slip model includes a geometric description layer, a constitutive relationship layer and a slip determination layer: The geometric description layer converts the joint surface attitude angle data, trace length dimension data, and opening width data extracted from the three-dimensional point cloud data into the normal vector coordinates, center point coordinates, and boundary contour coordinates of the joint surface through coordinate transformation algorithm and geometric projection algorithm, and establishes a spatial geometric description model of the joint surface; The constitutive relationship layer uses the friction coefficient data, normal stiffness data, tangential stiffness data, and roughness coefficient data of the joint surface as material parameter inputs. Through the calculation of the normal stress-displacement relationship and the tangential stress-displacement relationship, a nonlinear constitutive relationship model of the joint surface considering normal deformation and tangential slip is established. The slip determination layer compares the normal stress data and tangential stress data on the joint surface with the shear strength parameters of the joint surface, and determines the slip state and slip displacement increment of the joint surface through the slip condition determination algorithm and the slip direction calculation algorithm. The output data of the slip determination layer provides the joint surface mechanical response parameters and deformation boundary conditions for the rock mass sub-model.

[0031] In this example, a composite structural model encompassing the actual rock mass and reinforcement system effectively improves construction safety. The composite structural model integrates a rock mass sub-model, a support sub-model, and an interaction interface model to simulate the mechanical behavior of the rock mass and support, ensuring stability. The joint surface slip model, through geometric description, constitutive relations, and a slip determination layer, refines stress and slip analysis and optimizes safety assessments.

[0032] The minimum safety margin is obtained as: Apply the load disturbance of the next excavation to the composite structure model and conduct structural response analysis. During the calculation process, monitor the stress state of key units and nodes to determine the dangerous state of rock mass units and support units. The dangerous state determination process is as follows: calculate the safety factor of key units and nodes, which is defined as the ratio of the failure strength to the actual stress, select the minimum value of the safety factor of the important control section unit as the minimum safety margin of the composite structure, and record the unit position and failure mode corresponding to the minimum safety margin.

[0033] In this example, by applying load disturbances to the composite structure model and performing stress analysis, potential failure points are predicted, improving construction safety. Minimum safety margins are determined, enabling preemptive identification and strengthening of weak links to prevent accidents and reduce subsequent repair costs. Failure locations and patterns are also recorded, optimizing resource allocation and improving the targeted and efficient support design.

[0034] The specific process of triggering supplementary reinforcement is as follows: When the minimum safety margin is lower than the preset threshold, the unit position corresponding to the minimum safety margin is located and an early warning message is sent; Based on the failure mode, corresponding reinforcement alternatives are recommended from a preset library of standardized reinforcement measures, including the recommended location coordinates and technical parameter ranges for adding anchor rods, the recommended area range and thickness parameter range for adding shotcrete, and the recommended length and tension parameter range for setting prestressed anchor cables; The selected reinforcement scheme data is fed back to the reinforcement optimization module for re-optimization calculation, dynamic operation instructions are updated, and the preview calculation is repeated until the result meets the minimum safety margin greater than the preset threshold.

[0035] In this example, weak elements are located and early warnings are issued, providing timely mitigation of potential risks. By recommending targeted solutions from a standardized reinforcement library, such as adding anchor rods, increasing the thickness of shotcrete, or installing prestressed anchor cables, and providing precise parameters, efficient and economical reinforcement is ensured. The selected solution is fed back to the optimization module, where iterative calculations are performed until the safety margin is met, ensuring structural safety while optimizing resource allocation and reducing costs.

[0036] The present invention provides a system that integrates real-time isomorphic modeling, reinforcement optimization and safety decision-making. The synchronous modeling module obtains the structural characteristics of the excavation surface through three-dimensional point cloud scanning and convolutional neural networks, and generates an isomorphic structural mechanical model. Adaptive mesh simplification reduces the amount of calculation, and geological uncertainty assignment and load grading enhance the reliability of the model, providing a scientific basis for design and construction. The reinforcement optimization module uses sensor data and a modified hydration reaction kinetic model to predict the evolution of material strength, combines a multi-objective genetic algorithm to optimize support schemes and operation sequences, outputs dynamic instructions, improves safety and efficiency, and environmental correction and parameter calibration ensure accurate predictions. The safety decision-making module previews construction operations based on a composite structure model, calculates the minimum safety margin, triggers targeted reinforcement, reduces accident risks and repair costs, and specifically refers to Figure 3 The joint surface slip model refines mechanical analysis and optimizes resource allocation. This system integrates advanced technologies to achieve comprehensive optimization of safety, cost, and construction schedule, promoting the advancement of construction management technology.

[0037] Example 2:

[0038] As another specific embodiment of the present invention, the specific implementation process of the present invention is described in detail using a slope reinforcement project on the left bank of a reservoir dam as an application scenario. The rock mass is mainly granite with three sets of major joints, requiring combined support with anchor bolts and shotcrete.

[0039] As one embodiment of the present invention, the synchronous modeling module uses a 3D laser scanner to scan the excavated slope surface. The point cloud density is set to 1 point per square centimeter to ensure that the acquired point cloud data accurately reflects the detailed features of the slope surface. A scanning station is set 30 meters in front of the slope, using a multi-station combined scanning method. Each scanning station covers a 120-degree range, and adjacent stations overlap by at least 30%, ensuring the integrity and continuity of the point cloud data.

[0040] As an embodiment of the present invention, the pre-trained convolutional neural network model adopts an image recognition algorithm based on a deep residual network architecture. The network comprises 50 convolutional layers and uses weight parameters pre-trained on a rock engineering image database. The training database comprises rock surface images under different geological conditions, and each image is annotated with structural features such as the attitude angle, trace length, and opening width of the joint surface. The network model is capable of identifying the dip angle range, dip angle size, extension length, and opening degree of the joint surface. In this embodiment, three groups of main joint surfaces are identified, the first group of joint surfaces has a dip of 45 degrees northeast and a dip of 70 degrees, the second group of joint surfaces has a dip of 60 degrees northwest and a dip of 65 degrees, and the third group of joint surfaces has a dip of due north and a dip of 85 degrees.

[0041] The adaptive mesh simplification method at the geometric level dynamically adjusts mesh density based on the complexity of the rock surface. In areas with dense joints, the mesh size is set to 0.2 meters, while in relatively intact rock mass, the mesh size is increased to 1.5 meters. The mesh simplification criterion is based on the curvature change rate of adjacent point clouds. When the curvature change rate is greater than 0.15, the mesh is refined, while when the curvature change rate is less than 0.05, the mesh is coarsened. The resulting three-dimensional geometric unit contains 8,500 nodes and 15,000 tetrahedral elements, and the skewness, a mesh quality evaluation metric, is less than 0.6.

[0042] The physical property layer assigns rock mass parameters obtained from geological surveys to project zones. The parameters for the first, second, and third groups of joints are determined based on field sampling test results. To account for the uncertainty of geological parameters, the system sets upper and lower limits for each parameter. The elastic modulus is limited to ±20% of the standard value, and the strength parameter is limited to ±15% of the standard value.

[0043] The boundary condition layer simulates the step-by-step implementation of excavation and support through a graded load application algorithm. Excavation unloading follows a top-down, layered excavation construction sequence. Ground stress is applied according to the measured in-situ rock stress state, with a horizontal principal stress of 1.2 MPa and a vertical principal stress of 2.1 MPa. Groundwater pressure is applied based on water level monitoring data and the hydrostatic pressure distribution law. Construction loads include the dynamic load of excavation equipment and the static load of material stacking, which are converted into load boundary conditions for the corresponding nodes.

[0044] As one embodiment of the present invention, material strength evolution data is acquired in real time via sensors embedded within the anchor grouting. The sensor system includes wireless temperature sensors, humidity sensors, and resistivity sensors, installed at different locations within the anchor grouting holes. The temperature sensor has a measurement accuracy of ±0.2°C, the humidity sensor has a measurement accuracy of ±3% relative humidity, and the resistivity sensor has a measurement accuracy of ±2%. The sensor sampling frequency is set to once every three hours.

[0045] As an embodiment of the present invention, the modified hydration reaction kinetic model takes into account the impact of on-site environmental conditions on the hydration reaction rate. The environmental correction layer compares the measured temperature data with the standard curing temperature of 20 degrees Celsius. When the measured temperature is 15 degrees Celsius, the temperature correction coefficient is 0.7, and when the measured temperature is 25 degrees Celsius, the temperature correction coefficient is 1.3. The humidity correction layer compares the measured humidity with the standard humidity of 95%. The humidity correction coefficient decreases as the humidity decreases. When the humidity is 80%, the correction coefficient is 0.9. The pressure correction layer considers the impact of altitude on atmospheric pressure. The above correction coefficients are obtained through historical data and expert experience.

[0046] As one embodiment of the present invention, the hydration degree prediction layer calculates the hydration reaction degree using a numerical integration method. The reaction rate calculation layer comprehensively considers factors such as environmental correction parameters, cement composition data, water-cement ratio, and water-reducing agent addition to generate an actual hydration reaction rate curve that takes into account on-site conditions. The integral calculation uses a trapezoidal integration method with a time step of 1 hour. This calculation combines the mineral composition data of Portland cement and the patterns of hydration product formation to generate a hydration degree evolution curve with time as the variable.

[0047] As one embodiment of the present invention, a strength-hydration empirical relationship model converts hydration data into material strength parameters. The strength prediction layer calculates time-varying curves for compressive strength, tensile strength, and elastic modulus based on the hydration evolution curve, cement grade data, and mix design data, through strength development database query and multivariate regression analysis. The parameter correction layer uses strength test data from field-sampled cubic specimens for error analysis. The reliability assessment layer determines confidence intervals for each strength parameter by comparing historical engineering data with standard test data. The confidence level for compressive strength is 95%, and the coefficient of variation is 12%.

[0048] As one embodiment of the present invention, dynamic operation instructions are obtained through multi-objective genetic algorithm optimization. The optimization engine's population initialization layer sets anchor lengths to a discrete range of 6 to 12 meters, spacing to a discrete range of 1.5 to 3.0 meters, and grouting material options to include ordinary Portland cement slurry and cement-water glass dual-liquid slurry. The initial population size is set to 100 individuals, each containing four genes: anchor length, spacing, material type, and thickness.

[0049] The fitness evaluation layer comprehensively considers safety, economy, and timeliness. Safety factor calculations are based on structural mechanics analysis results; cost estimates include material, labor, and equipment costs; and construction period forecasts are based on construction quotas. The evolutionary operation layer uses tournament selection, single-point crossover, and uniform mutation operations, converging to a Pareto optimal solution set after 200 generations of evolution.

[0050] The final output dynamic operation instruction plan contains detailed construction process numbers, strength compliance triggering conditions, construction parameter ranges and completion judgment criteria.

[0051] As an embodiment of the present invention, the composite structural model integrates three sub-models: rock mass, support, and interaction interface. The rock mass sub-model is based on the geometric units and physical property data of the structural mechanics model, and uses the elastic-plastic constitutive relationship to describe the stress-strain behavior of the rock mass. When the rock mass stress exceeds the yield strength, the material enters the plastic state, and the strength parameters are reduced according to the Mohr-Coulomb failure criterion. The joint surface slip model establishes the spatial position relationship of the joint surface through the geometric description layer, the constitutive relationship layer determines the mechanical response according to the friction coefficient, normal stiffness, and tangential stiffness of the joint surface, and the slip judgment layer determines whether slip occurs based on the comparison of shear stress and shear strength.

[0052] The support sub-model uses beam elements to simulate the axial stress and bending deformation of the anchor rod. The rod diameter is set to 25 mm, and the material strength is determined according to the steel bar parameters. Shell elements simulate the internal surface stress and bending deformation of the shotcrete. The time-varying characteristics of the support system are dynamically updated through the material strength evolution data, and the strength parameters of the anchor rod grouting body at different ages are adjusted in real time.

[0053] The interaction interface model deals with the contact force transmission between the rock mass and the support. When the rock mass and the support undergo relative displacement, the contact force is calculated based on the contact stiffness. The deformation coordination condition ensures the displacement continuity on the contact surface, and the static equilibrium condition ensures that the force transmission satisfies Newton's third law.

[0054] As one embodiment of the present invention, the minimum safety margin is determined by applying the next excavation load perturbation to the composite structure model. The structural response analysis utilizes a nonlinear finite element method, accounting for the effects of material and geometric nonlinearity. The calculation focuses on monitoring the stress state of key elements within a 5-meter radius of the excavation face, including rock mass elements and support elements.

[0055] The dangerous state determination process is divided into three levels. First, the principal stress state of each unit is calculated to determine whether the tensile stress exceeds the tensile strength and the compressive stress exceeds the compressive strength. Then, the shear stress state is calculated to determine whether the Mohr-Coulomb failure criterion is met. Finally, the three failure modes of tension, compression, and shear are comprehensively considered and the corresponding safety factors are calculated. The tensile safety factor is defined as the ratio of the tensile strength to the maximum tensile stress, the compression safety factor is defined as the ratio of the compressive strength to the maximum compressive stress, and the shear safety factor is defined as the ratio of the shear strength to the maximum shear stress.

[0056] The system selects the minimum value of the safety factor among all key units as the minimum safety margin of the composite structure, and records the unit number, spatial coordinate position and failure mode type corresponding to the minimum value.

[0057] As one implementation of the present invention, when the minimum safety margin falls below a preset threshold, a supplementary reinforcement procedure is triggered. Warning information is sent simultaneously to project managers via mobile devices and on-site display screens. The warning includes the specific location of the hazardous unit, the safety margin value, the estimated time of failure, and recommended emergency measures.

[0058] After selecting a reinforcement scheme, the system feeds the scheme data back to the reinforcement optimization module for a new multi-objective optimization calculation. This optimization process considers the evolving material strength characteristics of the newly added reinforcement measures and updates the construction parameters and timing schedules in the dynamic work instructions. The safety decision module repeats pre-calculations of the updated scheme to verify that the reinforcement meets safety requirements. After two rounds of iterative calculations, the minimum safety margin for the combined reinforcement scheme is improved, meeting the safety threshold requirement of greater than 1.5. A construction authorization signal is then output, allowing the next excavation operation to proceed.

[0059] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A dynamic correction system for water conservancy project construction progress based on time series analysis, characterized in that: include: A synchronous modeling module is used to obtain point cloud data of the construction excavation surface through 3D point cloud scanning equipment, and use a pre-trained convolutional neural network model to identify and extract structural feature information of the excavation surface to generate a structural mechanics model; A reinforcement optimization module is used to perform multi-objective optimization of support schemes and operation sequences based on the structural mechanics model and combined with the material strength evolution data of the reinforcement materials, and output dynamic operation instructions; The safety decision module is used to perform pre-calculations on the construction operations in the dynamic operation instructions based on a composite structure model including a real rock structure and a real strength reinforcement system, and obtain the minimum safety margin of the composite structure. When the minimum safety margin is higher than a preset threshold, a construction authorization signal is output; when the minimum safety margin is lower than the preset threshold, a construction prohibition signal is output and supplementary reinforcement is triggered.

2. The dynamic correction system for water conservancy project construction progress based on time series analysis according to claim 1 is characterized by: The structural mechanics model includes a geometry layer, a physical property layer and a boundary condition layer; The geometric layer uses an adaptive mesh simplification method to convert the structural surface attitude angle, trace length, and opening width data in the 3D point cloud data into simplified 3D geometric unit node coordinates and unit connection relationships, generating simplified discretized geometric units containing the main control joint surface and fracture surface; The physical attribute layer uses a partition assignment method to assign the rock mass elastic modulus, Poisson's ratio, internal friction angle, cohesion data obtained from geological surveys, as well as the friction coefficient, normal stiffness, and tangential stiffness data of the structural surface to geometric units according to engineering partitions, and sets the parameter uncertainty range to form a structural mechanics model; The boundary condition layer uses a load grading algorithm to convert excavation unloading, ground stress, groundwater pressure, and construction load data into node force and displacement constraints of three-dimensional geometric unit nodes in stages. The geometric layer data provides the spatial positioning basis for the physical property layer, and the physical property layer data provides material response parameters for the boundary condition layer.

3. The dynamic correction system for water conservancy project construction progress based on time series analysis according to claim 1 is characterized by: The material strength evolution data is obtained in the following manner: Obtain sensor data from the anchor grouting material, use the modified hydration reaction kinetics model, input the collected sensor data into the maturity theory to obtain hydration data; By establishing an empirical strength-hydration relationship model, the hydration data are converted into time-varying trend data of compressive strength, tensile strength, and elastic modulus, generating a material strength evolution trend curve with time as the horizontal axis and strength parameter as the vertical axis.

4. The dynamic correction system for water conservancy project construction progress based on time series analysis according to claim 1 is characterized by: The dynamic job instruction acquisition method is: The structural mechanics model and material strength evolution data are input into a multi-objective genetic algorithm optimization engine, and the safety factor is set as the main constraint, and the construction cost and construction period are set as secondary optimization objectives; the optimization variables include the discrete range of anchor rod length, the discrete range of anchor rod spacing, the limited type of grouting material, and the thickness classification of shotcrete; the strong constraints include the minimum safety factor being greater than the value required by the specification and the material strength meeting the requirements of the design specification; through the weighted Pareto optimal solution screening method, the top three alternative solutions with the best comprehensive evaluation are selected from the constrained feasible solution set, and dynamic operation instructions containing the construction process number, strength compliance triggering condition, construction parameter range, and completion judgment standard are output.

5. The dynamic correction system for water conservancy project construction progress based on time series analysis according to claim 1 is characterized by: The composite structure model includes a rock mass sub-model, a support sub-model and an interaction interface model, specifically: The rock mass sub-model is based on the data in the geometric units and physical property layers of the structural mechanics model, and uses the elastic-plastic constitutive relationship and joint surface slip model to deal with the mechanical behavior of the main rock mass and structural surfaces; The support sub-model uses simplified beam elements to simulate anchor bolts and simplified shell elements to simulate shotcrete based on the time-varying trend data in the material strength evolution data, thus obtaining the staged mechanical behavior of the support system. The interaction interface model uses a linear contact algorithm to process the contact force transmission between the rock mass and the support. Through deformation coordination conditions and static equilibrium conditions, a composite structure model of the rock mass and support is formed. The rock mass sub-model data provides boundary conditions for the interaction interface, and the support sub-model data provides constraint parameters for the interaction interface.

6. The dynamic correction system for water conservancy project construction progress based on time series analysis according to claim 1 is characterized by: The minimum safety margin is obtained as: Apply the load disturbance of the next excavation to the composite structure model and conduct structural response analysis. During the calculation process, monitor the stress state of key units and nodes to determine the dangerous state of rock mass units and support units. The dangerous state determination process is as follows: calculate the safety factor of key units and nodes, which is defined as the ratio of the failure strength to the actual stress, select the minimum value of the safety factor of the important control section unit as the minimum safety margin of the composite structure, and record the unit position and failure mode corresponding to the minimum safety margin.

7. The dynamic correction system for water conservancy project construction progress based on time series analysis according to claim 1 is characterized by: The specific process of triggering supplementary reinforcement is as follows: When the minimum safety margin is lower than the preset threshold, the unit position corresponding to the minimum safety margin is located and an early warning message is sent; Based on the failure mode, corresponding reinforcement alternatives are recommended from a preset library of standardized reinforcement measures, including the recommended location coordinates and technical parameter ranges for adding anchor rods, the recommended area range and thickness parameter range for adding shotcrete, and the recommended length and tension parameter range for setting prestressed anchor cables; The selected reinforcement scheme data is fed back to the reinforcement optimization module for re-optimization calculation, dynamic operation instructions are updated, and the preview calculation is repeated until the result meets the minimum safety margin greater than the preset threshold.

Images