Engineering excavation progress dynamic estimation method, device and equipment

Abstract

The invention discloses an engineering excavation progress dynamic estimation method, device and equipment, and relates to the technical field of engineering project progress management, and the method comprises the steps: monitoring the position, posture and operation state of intelligent wearing equipment, and combining a BIM model and a dynamic engineering amount calculation model, meanwhile, an engineering quantity calculation model is dynamically adjusted according to the operation mode of the constructor and environmental data, the accuracy of progress estimation is ensured, and a progress situation map is generated to visually display the construction progress; the accuracy and real-time performance of construction progress management are improved, real-time estimation of the excavation progress and dynamic visual simulation of the construction progress are achieved, and a decision basis is provided for project management.

Description

Technical Field

[0001] This invention relates to the field of engineering project schedule management technology, and in particular to a method, apparatus and equipment for dynamically estimating the progress of engineering excavation. Background Technology

[0002] Currently, construction progress management primarily relies on traditional surveying methods and BIM models. These methods include on-site surveying using equipment such as total stations and BeiDou navigation systems, and design and simulation using BIM models. However, these technologies typically require specialized operators and complex data processing workflows, and struggle to achieve real-time data updates and progress estimation. Furthermore, existing technologies have limitations in integrating multi-source spatial data, making it difficult to achieve high-precision and real-time progress estimation and animation simulation. Therefore, there is an urgent need for a dynamic estimation method for construction excavation progress to improve the accuracy and real-time performance of construction progress estimation and to achieve dynamic and visual simulation of construction progress. Summary of the Invention

[0003] The main objective of this application is to provide a method, apparatus, and equipment for dynamic estimation of engineering excavation progress, aiming to solve the technical problem of how to improve the accuracy of real-time progress estimation in excavation projects.

[0004] To achieve the above objectives, this application proposes a method for dynamically estimating the progress of engineering excavation, comprising: Obtain the construction plan corresponding to the predicted construction area to determine the construction vehicle information and construction personnel information based on the construction plan, wherein the predicted construction area is dynamically generated based on the spatial boundary of the historical working face position; The current construction location is determined based on the construction vehicle information and the construction personnel information; Obtain a preset BIM model and combine it with the station line information corresponding to the current construction location to generate the excavation section result through a three-dimensional structure matching strategy; The excavation section results are input into the engineering quantity calculation model for calculation to obtain the engineering increment. The engineering quantity calculation model is dynamically adjusted based on the work mode and environmental data of the construction personnel information. The work mode is identified through the posture change data of the smart wearable device, and the smart wearable device is associated with the construction personnel information. The project progress model is updated based on the project increment and the current construction location. The project progress model dynamically generates a progress status map through a multi-level visualization engine.

[0005] In one embodiment, the step of determining the current construction location based on the construction vehicle information and the construction personnel information further includes: The location of the construction vehicle is obtained based on the construction vehicle information, and the current device location, posture change data, and operating status data of the associated smart wearable device and the construction equipment are obtained based on the construction personnel information. The operating status data is parsed to extract a first status data subset and a second status data subset, wherein the first status data subset is related to the working construction equipment, and the second status data subset is related to the moving direction of the working construction equipment; Construct a decision function, wherein the decision function is constructed based on the data duration and the combined weights of the excavation equipment; The attitude change data, the first state data subset, and the second data subset are input into the decision function to obtain the output value; When the output value exceeds the preset confidence threshold and the current device location of the smart wearable device is within the predicted construction area, and the current vehicle location of the construction vehicle is within the predicted construction area, the current device location is marked as a high confidence location. The current construction location is obtained by assisting in the verification of all the high-confidence locations.

[0006] In one embodiment, the step of inputting the attitude change data, the first subset of state data, and the second subset of data into the determination function to obtain an output value includes: The posture change data is converted into a sequence of action patterns. The matching degree of the action pattern sequence is calculated by comparing it with the preset excavation operation action spectrum to obtain the action matching degree. The action matching degree is input into the determination function for correction to obtain the target determination function; The first subset of state signals and the second subset of state signals are input into the target determination function to obtain the output value.

[0007] In one embodiment, the step of assisting in the verification of all the high-confidence locations to obtain the current construction location includes: Retrieve the location trajectories and signal strength of nearby smart wearable devices within the same construction period for all the aforementioned high-confidence locations; When the positioning trajectory of at least one smart wearable device in the neighboring area is stationary within the same time period, the spatiotemporal aggregation degree of personnel density and device signal strength is calculated. When the spatiotemporal aggregation degree exceeds the preset collaborative construction threshold, it is confirmed that there is a group work activity. The location with high credibility corresponding to the spatiotemporal aggregation degree is taken as the current construction location.

[0008] In one embodiment, the step of obtaining a preset BIM model and generating the excavation section result by combining it with the station line information corresponding to the current construction location through a three-dimensional structure matching strategy includes: The corresponding parametric section template in the preset BIM model is retrieved based on the station line information, and the section equation corresponding to the template is obtained. The collision point set between the probe ray and the three-dimensional geometric structure data in the BIM model is obtained, wherein the probe ray is uniformly distributed in a circumferential direction with the current construction position as the origin. An implicit boundary function is fitted to the actual contour based on the set of collision points; The implicit boundary function and the section equation are non-rigidly aligned to obtain the correction parameters; The cross-sectional equation is adjusted based on the correction parameters to generate the target cross-section; Perform a Boolean difference operation between the target cross-section and the BIM model to obtain the excavated cavity; The projection of the excavated cavity in the BIM model corresponding to the current construction position is output as the excavation section result.

[0009] In one embodiment, the step of inputting the excavation section result into the engineering quantity calculation model for calculation to obtain the engineering increment, wherein the engineering quantity calculation model is dynamically adjusted based on the work patterns of construction personnel and environmental data, and the work patterns of construction personnel are identified through posture change data, includes: The excavation cross-section results are discretized to generate a set of sampling points; A digital surface model of the current excavation face is formed based on the set of sampling points; Obtain the digital surface model from the previous construction cycle and calculate the spatial volume difference between the two surface models; Identify the work patterns of construction workers based on posture change data and determine the corresponding work efficiency coefficients; Environmental parameters are monitored, and environmental impact correction factors are calculated using a pre-set geotechnical mechanics model. The spatial volume difference, work efficiency coefficient, and environmental impact correction factor are input into the engineering quantity calculation model for multi-source data weighted fusion, and the engineering increment is output.

[0010] In one embodiment, the step of inputting the spatial volume difference, work efficiency coefficient, and environmental impact correction factor into the engineering quantity calculation model for multi-source data weighted fusion and outputting the engineering increment includes: Calculate the information entropy values ​​of the spatial volume difference, operation efficiency coefficient, and environmental impact correction factor; The first initial weight, the second initial weight, and the third initial weight are determined based on the information entropy value. The first initial weight corresponds to the spatial volume difference, the second initial weight corresponds to the operation efficiency coefficient, and the third initial weight corresponds to the environmental impact correction factor. Monitor the stability of the rock mass and the operating status of the construction equipment at the construction site. When an abnormality is detected, dynamically adjust the first initial weight, the second initial weight, and the third initial weight. The fluctuation of the spatial volume difference, operation efficiency coefficient and environmental impact correction factor within a preset time period is calculated using time series analysis. Based on the fluctuation, the first initial weight, the second initial weight and the third initial weight are penalized or rewarded to obtain a penalty function or a reward function. The penalty function or reward function is used to optimize and adjust the first initial weight, the second initial weight, and the third initial weight to obtain the first target weight, the second target weight, and the third target weight. The weighted fusion result is obtained by multiplying the first target weight, the second target weight, and the third target weight by the spatial volume difference, the operation efficiency coefficient, and the environmental impact correction factor, respectively. The uncertainty of the weighted fusion result is corrected based on probabilistic statistical methods, and the engineering increment is output.

[0011] In one embodiment, the step of updating the project progress model based on the project increment and the current construction location, and dynamically generating a progress status map based on the project progress model, includes: Establish an engineering progress model, discretize the construction site space into grid cells according to the design station number, and obtain the corresponding grid cell status. The grid cell status includes spatial coordinates, design engineering quantity, and time dimension attributes. Based on the current construction location, determine the construction grid unit, allocate the incremental engineering work to the construction grid unit according to spatial location, and obtain the actual completed engineering work volume; The expected completion time of the remaining work in a unit is calculated based on the actual completed work volume and the status of the grid unit. A multi-level progress status visualization engine is constructed to integrate the grid cell status, actual completed work volume, and expected completion time to generate a progress status map. By comparing and analyzing the progress status map and the construction plan, construction adjustment suggestions are generated.

[0012] Furthermore, to achieve the above objectives, this application also proposes a dynamic estimation device for engineering excavation progress, the dynamic estimation device for engineering excavation progress comprising: The acquisition module is used to acquire the construction plan corresponding to the predicted construction area in order to determine the construction vehicle information and construction personnel information based on the construction plan, wherein the predicted construction area is dynamically generated based on the spatial boundary of the historical working face position. The judgment module is used to determine the current construction location based on the construction vehicle information and the construction personnel information; The matching module is used to obtain a preset BIM model and generate the excavation section result by combining the station line information corresponding to the current construction location through a three-dimensional structure matching strategy. The calculation module is used to input the excavation section results into the engineering quantity calculation model for calculation to obtain the engineering increment. The engineering quantity calculation model is dynamically adjusted based on the work mode of the construction personnel and environmental data. The work mode of the construction personnel is identified through the posture change data of the smart wearable device. The display module is used to update the project progress model based on the project increment and the current construction location. The project progress model dynamically generates a progress status map through a multi-level visualization engine.

[0013] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the dynamic estimation method for engineering excavation progress as described above.

[0014] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the dynamic estimation method for engineering excavation progress as described above.

[0015] This application monitors the location, posture, and operating status of smart wearable devices, combines BIM models and dynamic engineering quantity calculation models, and dynamically adjusts the engineering quantity calculation model based on the work patterns of construction personnel and environmental data to ensure the accuracy of progress estimation. It also generates a progress status map to intuitively display the construction progress, thereby improving the accuracy and real-time nature of construction progress management and realizing real-time estimation of excavation progress and dynamic visualization simulation of construction progress. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1This is a flowchart illustrating the first embodiment of the dynamic estimation method for engineering excavation progress in this application. Figure 2 This is a flowchart illustrating the second embodiment of the dynamic estimation method for engineering excavation progress in this application. Figure 3 This is a flowchart illustrating the third embodiment of the dynamic estimation method for engineering excavation progress in this application. Figure 4 This is a flowchart illustrating the fourth embodiment of the dynamic estimation method for engineering excavation progress in this application; Figure 5 This is a schematic diagram of the module structure of the dynamic estimation device for the excavation progress of the project in this application. Figure 6 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the dynamic estimation method for engineering excavation progress in the embodiments of this application.

[0018] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0019] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0020] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0021] Currently, construction progress management primarily relies on traditional surveying methods and BIM models. These methods include on-site surveying using equipment such as total stations and BeiDou navigation systems, and design and simulation using BIM software. In addition, advanced technologies such as laser scanning and drones are also used to collect 3D data from construction sites. However, these technologies typically require specialized operators and complex data processing workflows, and real-time data updates and progress estimations are difficult to achieve. Furthermore, existing technologies have limitations in integrating multi-source spatial data, making it difficult to achieve high-precision and real-time progress estimation and animation simulation.

[0022] Therefore, this application proposes a dynamic estimation method for engineering excavation progress. The main solution of this application embodiment is as follows: First, obtain the construction plan corresponding to the predicted construction area to determine the construction vehicle information and construction personnel information based on the construction plan. The predicted construction area is dynamically generated based on the spatial boundaries of the historical tunnel face location. Second, determine the current construction location based on the construction vehicle information and construction personnel information. Third, obtain a preset BIM model and combine it with the station line information corresponding to the current construction location to generate excavation section results through a three-dimensional structure matching strategy. Fourth, input the excavation section results into the engineering quantity calculation model for calculation to obtain the engineering increment. The engineering quantity calculation model is dynamically adjusted based on the work mode and environmental data of the construction personnel information. The work mode is identified through posture change data from a smart wearable device, and the smart wearable device is associated with the construction personnel information. Fifth, update the engineering progress model based on the engineering increment and the current construction location. The engineering progress model dynamically generates a progress status map through a multi-level visualization engine.

[0023] Based on the above, this application also provides a method for dynamically estimating the progress of engineering excavation, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the dynamic estimation method for engineering excavation progress in this application.

[0024] In this embodiment, the dynamic estimation method for engineering excavation progress includes steps S10 to S50: Step S10: Obtain the construction plan corresponding to the predicted construction area to determine the construction vehicle information and construction personnel information based on the construction plan.

[0025] It should be noted that the predicted construction area refers to the operational space to be excavated in the next stage, as predicted by the system based on the current construction progress. This area is not fixed but dynamically evolves. The predicted construction area is dynamically generated based on the spatial boundaries of historical tunnel face locations. Historical tunnel face locations refer to the actual spatial locations of the front sections of tunnels or chambers that have completed several excavation cycles in the past. These locations are typically obtained through 3D scanning or positioning systems to obtain their point cloud contours, and the spatial boundaries are the geometric outer edges enclosed by these tunnel face contours. The system generates a predicted construction area that conforms to the current tunneling logic by fitting the center points, advancement directions, and section expansion trends (such as widening or turning) of these historical sections, using spatial interpolation and trend extrapolation algorithms.

[0026] Furthermore, the system associates the predicted construction area with the construction plan. The construction plan refers to the pre-set schedule in the project management system, which includes information such as task division, schedule, and resource allocation. The system extracts the task segment corresponding to the area and parses the associated construction vehicle information (such as equipment number, type (e.g., rock drilling rig, excavator, loader), work team, and pre-set work tasks) and construction personnel information (such as operator name, work team, and qualification certificate number). By comparing the actual monitored equipment and personnel locations, the system can verify whether the work is within the plan, thereby improving the accuracy of construction behavior identification and management compliance, and preventing resource misallocation or construction beyond designated boundaries.

[0027] Step S20: Determine the current construction location based on the construction vehicle information and construction personnel information.

[0028] It should be noted that the real-time location of the construction vehicles associated with the above information is obtained through positioning technology. This involves acquiring three-dimensional coordinates via onboard BeiDou, UWB, or inertial navigation modules, reflecting the actual location of the construction vehicles within the construction site. Simultaneously, the real-time location of the construction personnel is obtained, based on the spatial coordinates reported by the positioning chips in their smart safety helmets or wristbands.

[0029] When the real-time location of a construction vehicle falls within a predicted construction area dynamically generated based on historical tunnel face data, and its operational status data shows it is in an effective operating mode such as excavation or drilling, the system marks its location as a candidate construction point. Simultaneously, if the real-time location of the corresponding construction worker also enters this area, and their posture change data shows they are performing standard construction actions (such as leaning forward or periodically pushing their arms forward), the credibility of that location is further enhanced. Finally, the system employs a "human-machine collaborative verification" mechanism. When the equipment corresponding to the construction vehicle information and the personnel corresponding to the construction worker information simultaneously appear within the predicted construction area, and their behavioral characteristics meet the construction requirements, the location information of the team leader's smart wearable device is used as a reference for the real-time location due to its representativeness and authority. Therefore, on the construction site, the current construction location is generally the real-time location of the team leader's smart wearable device.

[0030] Step S30: Obtain the preset BIM model and generate the excavation section result by combining the station line information corresponding to the current construction location with the three-dimensional structure matching strategy.

[0031] It should be noted that the pre-set BIM model refers to the building information model established in the early stages of the project. It includes the three-dimensional geometry of the tunnel structure, material properties, design cross-sectional parameters, and spatial topological relationships, serving as a design benchmark for subsequent comparative analysis. The current construction location is a high-reliability work point coordinate determined by integrating real-time positioning data of construction vehicles and location information from smart wearable devices on construction personnel, and after multi-source verification. It represents the spatial location of the actual excavation face. The station line information is a coordinate system used to identify mileage in linear engineering. The station line information serves as a reference line to guide excavation and support work during construction. It is usually set by surveying equipment before construction and is used during construction to ensure the accuracy and consistency of the excavation cross-section, including data such as the location, direction, and spacing of the station. The three-dimensional structure matching strategy is a calculation method used to compare and match the actual construction location with the three-dimensional structure in the BIM model. By analyzing the spatial relationship between the construction location and the corresponding structure in the model, it generates a predicted result for the excavation cross-section. This strategy involves complex geometric calculations and spatial analysis to ensure that the generated excavation cross-section result is highly consistent with the actual construction situation.

[0032] Further, step S30 includes: First, retrieving the corresponding parametric cross-section template from the preset BIM model based on the stationing information, and obtaining the cross-section equation corresponding to the template. This template is a standard cross-sectional geometric model constructed based on design standards, which can be circular, horseshoe-shaped, rectangular, or other irregular structures, with adjustable dimensional parameters (such as radius, height, and width) to support flexible adaptation to the design requirements of different sections. Simultaneously, the system extracts the mathematical expression of the template, the cross-section equation, i.e., the implicit function or parametric equation describing the ideal design contour. Then, obtaining the collision point set between the probe rays and the three-dimensional geometric structure data in the BIM model, where the probe rays are uniformly distributed circumferentially outwards from the current construction location as the origin. The probe rays typically radiate radially at fixed angular intervals (e.g., one every 5° or 10°) within a horizontal or specified section, forming a scanning pattern covering the entire cross-section. Each ray extends along its direction vector and performs collision detection with the three-dimensional geometry (such as tunnel lining, surrounding rock boundary, support structure, etc.) in the BIM model. The system records the spatial coordinates of the first intersection of each ray with the model surface. All intersection points form a collision point set, which accurately reflects the theoretical boundary positions of the designed structure in each direction at the current construction location. Then, an implicit boundary function is fitted to the actual contour based on the collision point set, and the implicit boundary function and the section equation are non-rigidly aligned to obtain correction parameters. Specifically, the system uses curve or surface fitting algorithms (such as least squares, radial basis functions, or spline interpolation) to mathematically model these discrete points, constructing an implicit boundary function that describes the overall contour, for example, F(x, y) = 0, whose zero isosurface is the mathematical representation of the actual excavation boundary. This function not only smooths out measurement noise but also preserves local deformation characteristics, such as local over-excavation, collapse, or joint-affected areas. Subsequently, this implicit boundary function is non-rigidly aligned with the section equation from the design phase. Unlike rigid alignment, which only allows translation and rotation, non-rigid alignment allows for local deformation. An optimization algorithm calculates the deformation field from the design profile to the actual profile, outputting a set of correction parameters, including global offset, scaling factor, distortion factor, and local deformation weights, to accurately describe the geometric differences between the two. Next, the cross-sectional equation is adjusted based on the correction parameters to generate the target cross-section. A Boolean difference operation is performed between the target cross-section and the BIM model to obtain the excavation cavity. Finally, the projection of the excavation cavity in the BIM model corresponding to the current construction position is output as the excavation section result. Specifically, the system introduces correction parameters into the original cross-sectional equation (such as the mathematical expression for circular, horseshoe, or rectangular cross-sections) to dynamically correct the ideal geometry, generating a spatial closed curve that conforms to the actual site conditions—the target cross-section. This target cross-section not only preserves the overall topological characteristics of the designed structure but also realistically reflects local over-excavation, under-excavation, or deformation caused by geological conditions, construction disturbances, or support effects, achieving high fidelity.Subsequently, the target cross-section is extended in a limited manner along the tunnel axis (e.g., advancing one cycle advance) to form a three-dimensional swept volume. This swept volume is then compared to a pre-defined BIM model using a Boolean difference operation (i.e., subtracting the swept volume from the pre-defined BIM model). This operation geometrically simulates the actual excavation process, generating a cavity entity representing the removed rock mass (i.e., the excavated cavity). This cavity precisely corresponds to the actual excavation range of the current construction cycle, including all non-design-reserved local deformation areas. Finally, the system extracts the cross-sectional profile of the excavated cavity in the direction perpendicular to the tunnel axis and projects it onto the station plane corresponding to the current construction position, generating the excavation section result. This excavation section result is a three-dimensional model that details the actual shape and dimensions of the excavated chamber. This model includes not only the geometric information of the excavation section but may also include data such as material distribution and stress changes generated during the excavation process. Finally, the system outputs the verified excavation section results for the construction team to use. These results can be used for further quantity calculations, schedule analysis, and construction adjustments, thereby improving construction efficiency and quality.

[0033] Step S40: Input the excavation section results into the engineering quantity calculation model for calculation to obtain the engineering increment.

[0034] It should be noted that the engineering quantity calculation model is a highly dynamic and adaptive comprehensive algorithm model that can be adjusted according to real-time data from the construction site to ensure that the calculation of engineering increments is both accurate and timely. The core of this model lies in its ability to receive excavation section results and combine them with the work patterns of construction personnel and environmental data to calculate engineering increments, that is, the amount of work completed within a specific time period.

[0035] Furthermore, the engineering quantity calculation model is dynamically adjusted based on the work patterns and environmental data of construction personnel. Work patterns are identified through posture change data from smart wearable devices linked to the construction personnel information. A work pattern refers to the specific operation performed by the construction personnel during the work process, such as drilling, roughening, slag removal, or support preparation. Different patterns correspond to different construction efficiencies. This pattern is identified through posture change data collected by smart wearable devices (such as smart helmets and smart bracelets) linked to the construction personnel information. Posture change data includes body pitch angle, head movement trajectory, arm swing frequency, and acceleration time-series curves. The system uses a pattern recognition algorithm to convert this data into a categorizable action sequence and matches it with a preset standard work action spectrum to determine the current work type. For example, a continuous forward leaning and periodic pushing and pulling motion is identified as drilling, corresponding to a higher work efficiency coefficient. Environmental data, including rock joint density, moisture content, temperature, and rock mass stability, is acquired through on-site sensors or geological survey reports. After being input into a pre-set geotechnical mechanics model, an environmental impact correction factor is generated. This factor is used to calculate the non-manual excavation volume caused by rock loosening, spalling, or expansion. The aforementioned pre-set geotechnical mechanics model refers to a mathematical model established in the early stages of the project based on geological survey data, physical and mechanical parameters of the soil and rock mass, and engineering experience. This model describes and predicts the mechanical behavior of soil and rock mass under construction disturbances. Finally, the engineering quantity calculation model calculates the spatial volume difference (representing the theoretical excavation volume) based on the current and previous cycle's excavation cross-section results. Combined with dynamically adjusted work efficiency coefficients and environmental correction factors, a weighted fusion algorithm outputs a more realistic and reliable engineering increment, achieving a precise conversion from the geometric changes in project progress to numerical values.

[0036] Step S50: Update the project progress model based on the project increment and the current construction location. The project progress model dynamically generates a progress status map through a multi-level visualization engine.

[0037] It should be noted that incremental engineering work is allocated to corresponding construction units in the project schedule model based on spatial location. This project schedule model is a spatiotemporal integrated data structure built upon a pre-set BIM model, containing attributes such as design quantities, planned duration, actual completed quantities, remaining quantities, and timestamps for each construction segment. It supports refined management by station, cross-section, or grid unit. Whenever a new incremental engineering work is confirmed, the system updates the completion status of the corresponding unit and recalculates the cumulative completion rate and schedule deviation. Based on this, a multi-level visualization engine renders and dynamically displays the schedule data in layers. This engine supports multi-scale expression from macro to micro: the macro level displays a color-coded progress chart of the entire tunnel, using color depth to represent the completion percentage; the meso level presents a comparison between the actual excavation outline and the design cross-section of each tunnel face; and the micro level allows drilling down to the work trajectory and efficiency curves of specific equipment or work teams. Ultimately, the system integrates spatial location, workload, time dimension, and planned objectives to generate a progress status map. This map visually displays construction progress, lagging areas, and risk hotspots in the form of dynamic heat maps, trend curves, and 3D overlay models. It also supports automatic comparison with the original construction plan and generates construction adjustment suggestions. For example, if the comparison finds that the actual construction progress is lagging by 5 days, it will suggest adding work teams to increase construction efficiency, thus realizing a closed loop from data perception to management decision-making.

[0038] This embodiment monitors the location, posture, and operational status of smart wearable devices, combining BIM models and dynamic quantity calculation models to achieve real-time monitoring and estimation of tunnel excavation progress. The system can dynamically adjust the quantity calculation model based on the work patterns of construction personnel and environmental data, ensuring the accuracy of progress estimation. It also generates a progress status map to visually display the construction progress, improving the accuracy and real-time nature of construction progress management. This dynamic and visual simulation of construction progress provides a basis for project management decision-making.

[0039] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in Embodiment 1 above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 The dynamic estimation method for engineering excavation progress, step S20, further includes steps S201 to S206: Step S201: Obtain the location of the construction vehicle based on the construction vehicle information, and obtain the current device location, posture change data and operating status data of the associated smart wearable device based on the construction personnel information.

[0040] It should be noted that construction vehicle information refers to the identity and task attributes of the mechanical equipment assigned to the current operation in the construction plan, including equipment number, type (such as rock drilling rig, loader), work team, and preset work task. The system uses this information to locate specific equipment and collect its operational data. The construction vehicle location is a three-dimensional spatial coordinate data collected in real time by a positioning module installed on the equipment (such as a UWB ultra-wideband positioning tag, Beidou receiver, or inertial navigation unit), reflecting the actual location of the equipment in the tunnel or chamber. The update frequency is typically no less than 1Hz to ensure dynamic tracking accuracy. Construction personnel information refers to the identity data of the workers bound to the current construction task, including name, position, qualification number, and work team. The system uses this information to identify the personnel who should participate in the operation and associate it with their worn smart devices. Smart wearable devices refer to wearable devices integrating sensors and communication modules, such as smart safety helmets or smart bracelets, which are individually bound to specific construction personnel to collect their location and behavioral data. The current equipment location refers to the real-time spatial coordinates obtained by the smart wearable device through its built-in positioning chip, using the same coordinate system as the construction vehicle location for easy spatial comparison. Attitude change data refers to body motion information collected by the inertial measurement unit (IMU) built into the equipment, including triaxial acceleration, angular velocity, pitch angle, roll angle, and azimuth angle. This data is used to identify whether personnel are in specific working postures such as drilling, scaling, or cleaning. Construction equipment operating status data refers to mechanical operating parameters acquired through the equipment's CAN bus, PLC control system, or external sensors. This includes hydraulic pressure, drill bit speed, feed cylinder displacement, power head vibration spectrum, travel motor start / stop signals, and main power supply current. This data is used to determine whether the equipment is in an effective operating state. The system synchronously collects and time-aligns the above multi-source data, providing complete input for subsequent construction behavior identification and position reliability determination.

[0041] Step S202: parse the running status data and extract the first status data subset and the second status data subset.

[0042] It should be noted that the first subset of state data mentioned above is related to the working construction equipment. Specifically, it refers to the set of parameters directly related to whether the equipment is in an effective working condition. Typical parameters include hydraulic pressure value (reflecting the load size), drill bit speed (determining whether rotary operation is activated), propulsion cylinder displacement change rate (indicating whether the drill bit is advancing), and power head vibration intensity (identifying impact operations such as rock drilling). This subset is used to determine whether the equipment is performing substantive tasks such as excavation, drilling, or rock breaking, rather than idling or standby. The second subset of state data mentioned above is related to the movement direction of the working construction equipment. It mainly includes the start / stop status of the travel motor, equipment movement speed, heading angle, and acceleration vector, used to identify whether the equipment is currently in a fixed operation mode or a moving transfer mode. For example, when the travel motor is on and the speed is greater than a set threshold (e.g., 0.5 m / s), it indicates that the equipment is being transferred; if the heading angle continues to change, it may be in a reorientation process. By separating these two types of data, the system can effectively distinguish between "under construction" and "only moving" scenarios, avoiding misjudging the process of equipment entering and leaving the working face as excavation operation.

[0043] Step S203: Construct the decision function.

[0044] It should be noted that the decision function is a mathematical function based on rules or a weighted model. Its input is multi-source sensing data, and its output is a comprehensive score representing the probability of "construction in progress," used to determine whether the current state constitutes actual construction activity. The decision function is constructed based on the data duration and the weights of the excavation equipment combination. That is, the decision function is built upon two key factors: data duration and the weights of the excavation equipment combination. Data duration refers to the continuous length of time during which the first subset of data (e.g., increased hydraulic pressure, drill rotation, increased thrust displacement) and the second subset of data (e.g., equipment stationary or low-speed fine-tuning) simultaneously meet the construction conditions. The system sets a minimum effective duration threshold (e.g., 3 seconds). Signal fluctuations shorter than this duration are considered transient interference or equipment adjustments and are not counted as valid construction. Only when the relevant parameters consistently and stably exceed the threshold does the decision process begin, preventing false triggering. The weights of the excavation equipment combination refer to the pre-set parameter importance coefficients for different types of construction equipment or operation modes. For example, in drilling operations, the weights of propulsion cylinder displacement and hydraulic pressure are relatively high, while the drill string rotation speed is relatively low; whereas in loading operations, the weights of bucket movement and travel control are adjusted accordingly. These weights are obtained through field calibration or training with historical data, reflecting the contribution of each parameter to a specific operation.

[0045] Step S204: Input the attitude change data, the first state data subset, and the second data subset into the decision function to obtain the output value.

[0046] It should be noted that after these three types of data are synchronized and aligned in time, they are fed into a pre-built decision function as input variables.

[0047] Further, step S204 also includes: First, converting the posture change data into a sequence of action patterns. Specifically, posture change data refers to body motion information collected by the inertial measurement unit built into the device, including triaxial acceleration, angular velocity, pitch angle, roll angle, and azimuth angle, used to identify whether the personnel are in specific working postures such as drilling, shaving, and cleaning. The system processes this data in segments through a sliding window and uses pattern recognition algorithms (such as dynamic time warping or hidden Markov models) to convert it into a discrete sequence of action patterns, such as "standing → leaning forward → periodic pushing and pulling → retreating," which intuitively reflects the operation process of the construction personnel. Then, the action pattern sequence is matched with a preset excavation operation action spectrum to obtain the action matching degree. Specifically, the above action pattern sequence is matched with a preset excavation operation action spectrum, which is a typical action template library built based on standard construction processes, containing standard action sequences and their time characteristics for operations such as drilling, cleaning, and anchor bolt installation. A similarity score is calculated through a sequence comparison algorithm to obtain the action matching degree, which represents the degree of conformity between the current personnel operation and the standard operation. Then, the action matching degree is input into the judgment function for correction, resulting in the target judgment function. Specifically, the action matching degree is not used independently, but is input into the original judgment function as a dynamic adjustment factor to correct the weight distribution of each parameter. For example, when the matching degree is high, the weight of posture data in the judgment is increased, thereby enhancing the function's response sensitivity to standardized operations, ultimately forming the target judgment function and realizing the change from static rules to behavioral adaptation. Finally, the first and second state signal subsets are input into the target judgment function to obtain the output value. Specifically, the target judgment function multiplies the first and second state signal subsets with their corresponding weights and performs time integration or exponential decay weighting, ultimately generating a normalized output value in the interval [0, 1]. When this output value exceeds a preset confidence threshold, the system determines that the equipment is in an effective construction state. The aforementioned preset confidence threshold is a pre-set critical value (e.g., 0.8) used to distinguish between "suspected construction" and "confirmed construction." Only when the output value exceeds this threshold is it considered that there is substantial work behavior. This output value not only reflects whether the equipment is working, but also incorporates behavioral evidence of whether people are operating it correctly, thus improving the accuracy and reliability of construction status identification.

[0048] Step S205: When the output value exceeds the preset confidence threshold and the current device location of the smart wearable device is within the predicted construction area, and the current vehicle location of the construction vehicle is within the predicted construction area, the current device location is marked as a high confidence location.

[0049] It should be noted that the current device location of the smart wearable device refers to the real-time three-dimensional coordinates obtained by the wearable device (such as a smart safety helmet) bound to the construction worker via UWB or BeiDou positioning, used to determine whether the personnel have entered the work area. The current vehicle location of the construction vehicle is the spatial coordinates of the machinery obtained through the vehicle positioning module. The predicted construction area is the geographical range that may be excavated in the next stage, generated by a trend extrapolation algorithm based on the spatial boundary of the historical working face location. It has dynamic evolution characteristics, unlike fixed electronic fences. The system simultaneously judges three conditions: first, the output value meets the standard, indicating that the behavioral characteristics are credible; second, the personnel location is within the predicted area, indicating that they have not deviated from the task area; and third, the construction vehicle location is also within the same area, indicating that the equipment is in place. When all three conditions are met, it indicates that human-machine collaboration, standardized behavior, and accurate location are achieved. The system marks this location as a high-confidence location, serving as the basis for subsequent construction progress updates. This effectively avoids false alarms caused by a single signal mis-triggered (such as equipment passing by or personnel accidentally entering), improving the accuracy and reliability of construction location identification.

[0050] Step S206: Assist in verifying all high-confidence locations to obtain the current construction location.

[0051] It should be noted that after initially marking multiple high-confidence locations, they are not directly identified as the final construction locations. Instead, a collaborative analysis mechanism based on group behavior is introduced for cross-validation.

[0052] Further, step S206 includes: First, retrieving the location trajectories and signal strength of nearby smart wearable devices within the same construction period for all high-confidence locations. Specifically, the location trajectory refers to the spatial coordinate sequence of these devices over time, used to analyze personnel movement patterns. If the trajectory of a nearby device shows that it is continuously stationary within the same time period, it is determined that the person may be performing fixed work (such as operating equipment or observing the drilling process), rather than passing by or inspecting. Subsequently, when at least one of the location trajectories of the nearby smart wearable devices is stationary within the same time period, the spatiotemporal aggregation degree of personnel density and device signal strength is calculated. Specifically, when multiple nearby devices are stationary, the personnel density is further calculated, i.e., the number of construction personnel simultaneously present and working within a unit area, reflecting the concentration of work; at the same time, the signal strength of each device is collected to analyze the spatial distribution stability of wireless signals and eliminate signal drift or obstruction interference. The personnel density and signal strength are spatiotemporally aligned to construct a spatiotemporal aggregation degree index, which comprehensively reflects personnel aggregation, location stability, and signal consistency. The higher the value, the greater the possibility of multiple people working together. Finally, when the spatiotemporal aggregation degree exceeds the preset collaborative construction threshold, a group work activity is confirmed, and the high-confidence location corresponding to the spatiotemporal aggregation degree is taken as the current construction location. Specifically, when the spatial aggregation degree exceeds the preset collaborative construction threshold, the system determines that a group work activity exists, indicating that the current activity is not an isolated event or a false trigger, but a real and organized construction process. The aforementioned preset collaborative construction threshold is a pre-set quantitative standard used in the construction behavior recognition system to determine whether a group work activity exists; its function is to distinguish between "isolated events" and "real collaborative construction." This threshold is a normalized value (usually in the range of 0 to 1), representing a comprehensive score of the degree of aggregation of personnel density and equipment signal strength in time and space. Ultimately, the system confirms the high-confidence location corresponding to this spatiotemporal aggregation degree as the current construction location, achieving a transition from individual judgment to group verification, thereby improving the accuracy, robustness, and project credibility of construction location identification.

[0053] This embodiment integrates information on construction vehicles and personnel, and utilizes location, attitude change, and equipment operating status data collected by intelligent devices to construct a decision function to evaluate construction activities. When the data confidence level exceeds a threshold and the equipment is located within the predicted area, it is marked as a high-confidence location. Through verification, the precise construction location is obtained, effectively distinguishing between actual operations and false triggers, and improving the accuracy and reliability of construction location judgment.

[0054] Based on the first embodiment of this application, in the third embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3The dynamic estimation step S40 of the engineering excavation progress further includes steps S301 to S306: Step S301: Discretize the excavation section results to generate a set of sampling points.

[0055] It should be noted that because the excavation cross-section results contain irregular shapes, local spalling, or over- and under-excavation areas, they are difficult to use directly for volume calculations and therefore require discretization. This process involves converting continuous geometric boundaries or filled areas into a finite number of discrete spatial points, i.e., a sampling point set. The system employs either a regular or adaptive sampling strategy: regular sampling generates grid points within the cross-section at fixed intervals (e.g., every 0.2 meters) to determine whether they are located within the excavation area; adaptive sampling increases point density in areas with large curvature or drastic boundary changes (e.g., corners, fracture-developed areas) while reducing sampling in straight sections to balance accuracy and computational efficiency. The spatial coordinates of the sampling points are typically represented in three dimensions (x, y, z) with attached attribute labels (e.g., whether within the design contour, distance from the boundary, etc.). The generated sampling point set includes not only points on the boundary but also internal filled points, forming a digital representation of the entire excavation cross-section. This point set serves as the basic input for subsequently building the Digital Surface Model (DSM), used for spatial registration and volume difference calculation with the sampling point set from the previous cycle.

[0056] Step S302: Form a digital surface model of the current excavation face based on the set of sampling points.

[0057] It should be noted that the sampling point set is an ordered set of spatial points generated by discretizing the excavation cross-section results. The system employs surface reconstruction algorithms, such as moving least squares, Poisson surface reconstruction, or triangulation, to fit and connect these discrete points, generating a continuous, smooth, and realistically reflective digital surface model of the excavation face. This model is expressed in mesh form, consisting of vertices, edges, and faces, accurately depicting the undulations, depressions, and over-excavation areas of the excavation face. During reconstruction, the mesh resolution can be dynamically adjusted according to the point density, maintaining high fidelity even in complex areas.

[0058] Step S303: Obtain the digital surface model of the previous construction cycle and calculate the spatial volume difference between the two surface models.

[0059] It should be noted that the digital surface model of the previous construction cycle refers to the three-dimensional geometric representation of the tunnel face that has been confirmed and archived in the previous excavation cycle. It is typically stored in the form of a triangular mesh, reflecting the final excavation shape of the previous period. The system spatially aligns the current excavation face digital surface model generated in the current construction cycle with this model, using the ICP algorithm or a coordinate matching method based on station lines to ensure accurate registration of the two models in a unified coordinate system. Subsequently, through voxelization or section integration, the spatial region between the two models is divided into small volume elements, and the total volume difference between them is calculated. This total volume difference, i.e., the spatial volume difference (representing the theoretically removed rock mass volume in this excavation), is the geometric basis for the engineering increment.

[0060] Step S304: Identify the working mode of the construction workers based on the posture change data and determine the corresponding work efficiency coefficient.

[0061] It should be noted that attitude change data refers to body motion information collected by the device's built-in inertial measurement unit, including triaxial acceleration, angular velocity, pitch angle, roll angle, and azimuth angle. This data is used to identify whether personnel are in specific work postures such as drilling, shaving, or cleaning. The system performs time-domain and frequency-domain analysis on the attitude change data, extracting key motion features, such as periodic pushing and pulling (drilling), up-and-down swinging (cleaning), or static observation. It then uses pattern recognition algorithms (such as support vector machines or LSTM neural networks) to classify these features into specific work modes, such as "continuous standard drilling," "intermittent operation," and "no effective movement." Each work mode corresponds to a preset work efficiency coefficient, determined based on on-site calibration data or time studies, used to quantify the contribution of different behaviors to the actual excavation progress. For example, "continuous standard drilling" corresponds to an efficiency coefficient of 0.9, "intermittent operation" to 0.6, and "no effective movement" to 0.1. By mapping the identified working modes to corresponding efficiency coefficients, the system can dynamically adjust the theoretical excavation volume in the engineering quantity calculation, eliminate the influence of invalid operation time, and make the engineering increment more accurately reflect the actual construction output.

[0062] Step S305: Monitor environmental parameters and calculate environmental impact correction factors using a preset geotechnical mechanics model.

[0063] It should be noted that environmental parameters include the degree of joint development in the surrounding rock, fissure water pressure, temperature changes, humidity, the extent of loosened rock zones, and the state of in-situ stress. These parameters are acquired in real time through on-site sensors (such as piezometers, temperature and humidity probes, and acoustic detectors) or geological survey data. These parameters directly affect the stability and self-stabilizing capacity of the rock mass, and may lead to natural spalling or local collapse without manual excavation. The system inputs the above environmental parameters into a preset geotechnical mechanics model. This preset geotechnical mechanics model refers to a mathematical model established in the early stages of the project based on geological survey data, physical and mechanical parameters of the rock and soil, and engineering experience. It is used to describe and predict the mechanical behavior of rock and soil under construction disturbance and can predict the failure trend and loosening range of the rock mass under the current geological and environmental conditions. The model output is an environmental impact correction factor, which is a dimensionless coefficient reflecting the amount of passive excavation.

[0064] Step S306: Input the spatial volume difference, operation efficiency coefficient and environmental impact correction factor into the engineering quantity calculation model for multi-source data weighted fusion, and output the engineering increment.

[0065] It should be noted that multi-source data weighted fusion is a complex process that involves the allocation of weights to different data sources and comprehensive analysis.

[0066] Further, step S306 includes: first calculating the spatial volume difference. Operational efficiency coefficient Environmental impact correction factor The information entropy values ​​were obtained respectively. , and Subsequently, based on the information entropy value, the first initial weight, the second initial weight, and the third initial weight are determined. The first initial weight corresponds to the aforementioned spatial volume difference, the second initial weight corresponds to the aforementioned operational efficiency coefficient, and the third initial weight corresponds to the aforementioned environmental impact correction factor, specifically satisfying the following: in, You can take the difference in spatial volume. Operational efficiency coefficient Environmental impact correction factor , This represents the sum of total determinism across all data sources, for example... , and ,So Then the first initial weight Second initial weights Third initial weight .

[0067] Subsequently, the stability of the rock mass and the operating status of the construction equipment at the construction site are monitored. When an abnormality is detected, the first, second, and third initial weights are dynamically adjusted. Specifically, when the system monitors the stability of the rock mass (e.g., the frequency of microseismic events) and the operating status of the construction equipment (e.g., fault alarms), and an anomaly is detected, the weights of the data affected by these anomalies are automatically reduced. For example, if the rock mass becomes unstable, the environmental impact correction factor is reduced. The initial weights are assigned to prevent over-adjustment. Then, time series analysis is used to calculate the fluctuations of spatial volume difference, operational efficiency coefficient, and environmental impact correction factor within a preset time period. Based on the degree of fluctuation, the first, second, and third initial weights are penalized or rewarded to obtain a penalty function or reward function. Specifically, time series analysis (such as sliding standard deviation) is used to calculate the fluctuations of each variable within a preset time period (such as the most recent three cycles). When the fluctuation is large, a penalty function is applied. If the fluctuation is small or stable, a reward function is applied. ,in Representing variables The degree of fluctuation within a preset time period is usually expressed as the moving standard deviation or coefficient of variation. Greater fluctuation indicates greater data instability. In the penalty function, when... When it is large, Decrease, thereby reducing the corresponding weight. As the adjustment coefficient, in the reward function when When smaller, This increases the corresponding weight. This is the gain coefficient.

[0068] The first initial weight, second initial weight, and third initial weight are optimized and adjusted using a penalty function or a reward function to obtain the first target weight. Second objective weights and the third objective weight ; The weighted fusion result is obtained by multiplying the weights of the first objective, the second objective, and the third objective by the spatial volume difference, the operational efficiency coefficient, and the environmental impact correction factor, respectively, and then summing the results. Specifically, it is expressed as follows: in, The weighted fusion result represents a preliminary estimate of the engineering increment, but uncertainties remain due to measurement errors, model biases, and random fluctuations. To quantify these uncertainties, probabilistic statistical methods are used to correct the uncertainty of the weighted fusion result, outputting the engineering increment. Specifically, the system employs probabilistic statistical methods, such as Monte Carlo simulation, Bayesian estimation, or confidence interval analysis, to model the distribution characteristics of the input variables. For example, spatial volume differences are treated as a normal distribution, operational efficiency coefficients are sampled according to empirical distributions, and environmental factors are considered within their confidence ranges. Random sampling is used to simulate the distribution pattern of the output results. This yields the expected value, standard deviation, and 95% confidence interval of the engineering increment, transforming it from a single-point estimate to a probabilistic output. This process effectively identifies high-risk sources of deviation, preventing overall misjudgment due to anomalies in a single data point.

[0069] This embodiment generates a sampling point set by discretizing the excavation section results, constructs a digital surface model, and calculates the spatial volume difference with the previous construction cycle model. Combining attitude change data and environmental parameters, it identifies the working mode, determines the operation efficiency coefficient and environmental impact correction factor, and finally calculates the project increment by weighted fusion of these multi-source data. This achieves high-precision, dynamic, and quantifiable intelligent perception of construction progress, improving the scientific nature and reliability of project management.

[0070] Based on the first embodiment of this application, in the fourth embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 4 The dynamic estimation step S50 of the engineering excavation progress further includes steps S401 to S405: Step S401: Establish an engineering progress model, discretize the construction site space into grid cells according to the design station number, and obtain the corresponding grid cell status.

[0071] It should be noted that establishing a project schedule model is a fundamental step in achieving digital management of the construction process. This model is based on the design BIM model and constructed by combining the spatial organization characteristics of linear projects. The project schedule model is a multi-dimensional data structure that integrates geometric, attribute, and temporal information, used to record and update the actual progress status of each construction segment.

[0072] Specifically, the system first divides the construction site space in an orderly manner according to the design station numbers in the design drawings. The design station numbers are mileage markers along the tunnel axis, represented in the format "K+M" (for example, K10+500 represents the position where the cumulative distance along the centerline is 10,500 meters from the starting point of the route design), and have clear geographical orientation. Based on this, the system discretizes the continuous space at fixed intervals (such as every 2 meters or every 5 meters), dividing it into a series of continuous grid units. Each grid unit represents an independent construction management unit, forming a sequenced spatial container distributed along the axis. Meanwhile, the aforementioned grid cells include different grid cell states, which include spatial coordinates, design quantities, and time-related attributes. Specifically, each grid cell not only contains its spatial coordinates (including the three-dimensional coordinates of the center point, the coordinates of the boundary vertices, and the chainage range), but also associates key attribute information: first, the design quantities, i.e., the theoretical excavation volume or support area corresponding to the cell in the BIM model, serving as the benchmark value for progress calculation; second, time-related attributes, including the planned start time, planned completion time, actual start time, current cumulative completion volume, and construction cycle number, supporting traceability of the construction process along a timeline. Furthermore, grid cells can also be expanded to store additional information such as construction teams, equipment types, and geological conditions.

[0073] Step S402: Determine the construction grid unit based on the current construction location, allocate the incremental work to the construction grid unit according to the spatial location, and obtain the actual completed work volume.

[0074] It should be noted that by accurately locating the current construction site, the grid cells under construction can be determined. This process typically relies on high-precision positioning systems, such as BeiDou, laser scanning, or BIM model-based positioning technologies, to ensure the accuracy of the construction location.

[0075] Once the construction grid cells are determined, the calculated project increments can be allocated to the corresponding grid cells according to their spatial location. Project increments refer to the amount of work completed within a specific time period, which can be calculated based on the construction schedule model and actual construction data. Allocating project increments to construction grid cells facilitates more detailed management and monitoring of construction progress.

[0076] Obtaining the actual completed work volume is achieved by comparing the incremental work volume allocated to grid cells with the actual construction results. This involves assessing construction quality and quantifying the completed work. The data on the actual completed work volume can be used to update the construction schedule model, provide real-time feedback for project management, and provide a basis for subsequent construction activities.

[0077] Step S403: Calculate the expected completion time of the remaining work in the unit based on the actual completed work volume and the status of the grid unit.

[0078] It should be noted that the actual completed work volume refers to the effective excavation volume accumulated and allocated to a certain construction grid unit in the current construction cycle, reflecting the actual construction progress of that section; the grid unit status contains complete attribute information of the unit, especially the designed work volume (i.e., the theoretical total excavation volume), planned start and finish times, construction teams, equipment configuration, and current completion rate. The system first calculates the remaining work volume of the unit, which is the designed work volume minus the actual completed work volume. Subsequently, it combines historical construction data (such as the average daily advance or excavation efficiency per unit time in the last three cycles) and considers the current work mode, number of personnel, and environmental impact factors to dynamically estimate the current work efficiency level. Based on the above work efficiency level, linear extrapolation or trend-weighted algorithms are used to calculate the time required to complete the remaining work volume. Finally, the current time is added to the required construction period to obtain the expected completion time.

[0079] Step S404: Construct a multi-level progress status visualization engine to integrate grid cell status, actual completed work volume, and expected completion time to generate a progress status map.

[0080] It should be noted that the purpose of building a multi-level progress status visualization engine is to provide an intuitive and dynamic construction progress display platform. This engine can integrate key information such as grid cell status, actual completed work volume, and expected completion time, and transform this data into an easy-to-understand progress status map. This map supports multi-level representation: the macro level displays the overall progress as a color-coded strip along the route axis, with color intensity indicating the completion rate of each segment (e.g., green for ahead of schedule, yellow for normal, and red for lagging); the meso level highlights the current construction grid cell in the 3D BIM model, overlaying a comparison between the actual excavation face and the design outline; the micro level extends to individual cells, displaying their completion percentage, remaining time, and construction team information. This map can include various visualization elements, such as color-coded progress bars, milestone markers on the timeline, and dynamically updated construction progress heatmaps.

[0081] Step S405: Compare and analyze the progress status map and the construction plan to generate construction adjustment suggestions.

[0082] It should be noted that comparative analysis typically involves a detailed comparison between the current progress shown in the progress status map and the pre-set construction plan. This may include assessing the completion status of each construction phase, resource utilization efficiency, and the achievement time of key milestones. During the analysis, the system may use statistical methods, predictive models, or machine learning algorithms to predict the impact of schedule deviations on the entire project and propose corresponding adjustment suggestions.

[0083] The generated construction adjustment recommendations include reallocating resources, adjusting the construction sequence, increasing manpower or equipment, extending working hours, or introducing new construction technologies. These recommendations aim to optimize the construction process, improve efficiency, and ensure the project is completed on schedule or more efficiently. Furthermore, construction adjustment recommendations can help the project team better understand the dynamic changes during construction and improve their adaptability to uncertainty. By implementing these recommendations, the project team can reduce the risk of delays, control costs, and improve the overall success rate of the project.

[0084] This embodiment establishes a project progress model, dividing the construction site into grid cells and updating their status in real time, including spatial coordinates, workload, and time attributes. By intelligently allocating incremental work, it predicts the completion time of the remaining workload and generates a progress status map using a multi-level visualization engine. Simultaneously, by comparing and analyzing the map with the plan, it automatically proposes construction adjustment suggestions, which helps to achieve precise control and dynamic management of the construction process and improve the overall project execution efficiency.

[0085] Based on the first embodiment of this application, this application also provides a device for dynamically estimating the progress of engineering excavation. Please refer to... Figure 5 The device includes: The acquisition module 10 is used to acquire the construction plan corresponding to the predicted construction area in order to determine the construction vehicle information and construction personnel information based on the construction plan. The predicted construction area is dynamically generated based on the spatial boundary of the historical working face position.

[0086] The judgment module 20 is used to determine the current construction location based on the construction vehicle information and the construction personnel information.

[0087] The matching module 30 is used to obtain the preset BIM model and generate the excavation section result by combining the station line information corresponding to the current construction location through a three-dimensional structure matching strategy.

[0088] The calculation module 40 is used to input the excavation section results into the engineering quantity calculation model for calculation to obtain the engineering increment. The engineering quantity calculation model is dynamically adjusted based on the work mode of the construction personnel and environmental data. The work mode of the construction personnel is identified through the posture change data of the smart wearable device.

[0089] The display module 50 is used to update the project progress model based on the project increment and the current construction location. The project progress model dynamically generates a progress status map through a multi-level visualization engine.

[0090] The dynamic estimation device for excavation progress provided in this application, employing the dynamic estimation method for excavation progress in the above embodiments, can solve the technical problem of how to improve the accuracy of real-time progress estimation in excavation projects. Compared with the prior art, the beneficial effects of the dynamic estimation device for excavation progress provided in this application are the same as those of the dynamic estimation method for excavation progress provided in the above embodiments, and other technical features in the dynamic estimation device for excavation progress are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0091] In one embodiment, the judgment module 20 is further configured to: obtain the location of the construction vehicle based on the construction vehicle information; and obtain the current device location, posture change data, and operating status data of the associated smart wearable device based on the construction personnel information; parse the operating status data to extract a first state data subset and a second state data subset, wherein the first state data subset is related to the working construction equipment, and the second state data subset is related to the moving direction of the working construction equipment; construct a judgment function based on the data duration and the combined weight of the excavation equipment; input the posture change data, the first state data subset, and the second data subset into the judgment function to obtain an output value; when the output value exceeds a preset confidence threshold and the current device location of the smart wearable device is within the predicted construction area, and the current vehicle location of the construction vehicle is within the predicted construction area, mark the current device location as a high-confidence location; and perform assisted verification on all the high-confidence locations to obtain the current construction location.

[0092] In one embodiment, the judgment module 20 is further configured to convert the posture change data into an action pattern sequence; calculate the matching degree between the action pattern sequence and a preset excavation operation action spectrum to obtain an action matching degree; input the action matching degree into the judgment function for correction to obtain a target judgment function; and input the first state signal subset and the second state signal subset into the target judgment function to obtain an output value.

[0093] In one embodiment, the judgment module 20 is further configured to retrieve the positioning trajectories and signal strength of nearby smart wearable devices within the same construction period for all the high-confidence locations; when the positioning trajectories of at least one of the nearby smart wearable devices are stationary within the same time period, calculate the spatiotemporal aggregation degree of personnel density and device signal strength; when the spatiotemporal aggregation degree exceeds a preset collaborative construction threshold, confirm the existence of group work activities; and use the high-confidence location corresponding to the spatiotemporal aggregation degree as the current construction location.

[0094] In one embodiment, the matching module 30 is further configured to retrieve the corresponding parametric section template in the BIM model based on the stationing information, and obtain the section equation corresponding to the template; obtain the collision point set between the probe ray and the three-dimensional geometric structure data in the BIM model, wherein the probe ray is uniformly distributed in a circumferential direction with the current construction position as the origin; fit an implicit boundary function of the actual contour based on the collision point set; perform non-rigid alignment between the implicit boundary function and the section equation to obtain correction parameters; adjust the section equation based on the correction parameters to generate a target section; perform Boolean difference operation on the target section and the BIM model to obtain the excavation cavity; and output the projection of the excavation cavity in the BIM model corresponding to the current construction position as the excavation section result.

[0095] In one embodiment, the calculation module 40 is further configured to discretize the excavation section results to generate a set of sampling points; form a digital surface model of the current excavation face based on the set of sampling points; obtain the digital surface model of the previous construction cycle and calculate the spatial volume difference between the two surface models; identify the working mode of the construction personnel based on the posture change data and determine the corresponding work efficiency coefficient; monitor environmental parameters and calculate the environmental impact correction factor through a preset geotechnical mechanics model; input the spatial volume difference, work efficiency coefficient and environmental impact correction factor into the engineering quantity calculation model for multi-source data weighted fusion and output the engineering increment.

[0096] In one embodiment, the calculation module 40 is further configured to calculate the information entropy values ​​of the spatial volume difference, the work efficiency coefficient, and the environmental impact correction factor; determine a first initial weight, a second initial weight, and a third initial weight based on the information entropy values, wherein the first initial weight corresponds to the spatial volume difference, the second initial weight corresponds to the work efficiency coefficient, and the third initial weight corresponds to the environmental impact correction factor; monitor the rock mass stability and the operating status of the construction equipment at the construction site, and dynamically adjust the first initial weight, the second initial weight, and the third initial weight when an abnormality is detected; and calculate the spatial volume difference, the work efficiency coefficient, and the environmental impact correction factor using a time series analysis method. The fluctuation degree of the impact correction factor within a preset time period is analyzed. Based on the fluctuation degree, the first initial weight, the second initial weight, and the third initial weight are penalized or rewarded to obtain a penalty function or a reward function. The first initial weight, the second initial weight, and the third initial weight are optimized and adjusted using the penalty function or reward function to obtain a first target weight, a second target weight, and a third target weight. The first target weight, the second target weight, and the third target weight are multiplied by the spatial volume difference, the operation efficiency coefficient, and the environmental impact correction factor, respectively, and then summed to obtain a weighted fusion result. The uncertainty of the weighted fusion result is corrected based on a probabilistic statistical method, and the engineering increment is output.

[0097] In one embodiment, the display module 50 is further configured to establish an engineering progress model, discretize the construction site space into grid units according to the design station number and obtain the corresponding grid unit status, wherein the grid unit status includes spatial coordinates, design engineering quantity, and time dimension attributes; determine construction grid units according to the current construction location, allocate the engineering increment to the construction grid units according to the spatial location and obtain the actual completed engineering quantity; calculate the expected completion time of the remaining engineering quantity of the unit based on the actual completed engineering quantity and the grid unit status; construct a multi-level progress status visualization engine, integrate the grid unit status, actual completed engineering quantity, and expected completion time to generate a progress status map; and compare and analyze the progress status map with the construction plan to generate construction adjustment suggestions.

[0098] This application provides a dynamic estimation device for engineering excavation progress, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the dynamic estimation method for engineering excavation progress in Embodiment 1 described above.

[0099] The following is for reference. Figure 6 The diagram illustrates a structural schematic suitable for implementing a dynamic estimation device for engineering excavation progress in the embodiments of this application. The dynamic estimation device for engineering excavation progress in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 6 The illustrated dynamic estimation device for engineering excavation progress is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0100] like Figure 6As shown, the dynamic estimation device for excavation progress may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1002 or a program loaded from storage device 1003 into random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the dynamic estimation device for excavation progress. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following can be connected to I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the engineering excavation progress dynamic estimation device to communicate wirelessly or wiredly with other devices to exchange data. Although various engineering excavation progress dynamic estimation devices are shown in the figures, it should be understood that implementation or possession of all of them is not required. More or fewer may be implemented alternatively.

[0101] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0102] The dynamic estimation device for excavation progress provided in this application, employing the dynamic estimation method for excavation progress in the above embodiments, can solve the technical problem of how to improve the accuracy of real-time progress estimation in excavation projects. Compared with the prior art, the beneficial effects of the dynamic estimation device for excavation progress provided in this application are the same as those of the dynamic estimation method for excavation progress provided in the above embodiments, and other technical features of this dynamic estimation device for excavation progress are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0103] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0104] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0105] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the dynamic estimation method for engineering excavation progress in the above embodiments.

[0106] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible storage medium containing or storing a program that can be executed by instructions, used by a device, or used in conjunction with it. The program code contained on the computer-readable storage medium may be transmitted using any suitable storage medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0107] The aforementioned computer-readable storage medium may be included in the dynamic estimation device for excavation progress; or it may exist independently and not be assembled into the dynamic estimation device for excavation progress.

[0108] The aforementioned computer-readable storage medium carries one or more programs that, when executed by the dynamic estimation device for excavation progress, enable the device to write computer program code for performing the operations of this application in one or more programming languages ​​or a combination thereof. These programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, and C++—and conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0109] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using dedicated hardware-based implementations that perform the specified functions or operations, or can be implemented using a combination of dedicated hardware and computer instructions.

[0110] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0111] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described dynamic estimation method for excavation progress, thereby solving the technical problem of how to improve the accuracy of real-time progress estimation in excavation projects. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the dynamic estimation method for excavation progress provided in the above embodiments, and will not be repeated here.

[0112] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described dynamic estimation method for engineering excavation progress.

[0113] The computer program product provided in this application can solve the technical problem of how to improve the accuracy of real-time progress estimation in excavation projects. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the dynamic excavation progress estimation method provided in the above embodiments, and will not be repeated here.

[0114] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for dynamically estimating the progress of engineering excavation, characterized in that, include: Obtain the construction plan corresponding to the predicted construction area to determine the construction vehicle information and construction personnel information based on the construction plan, wherein the predicted construction area is dynamically generated based on the spatial boundary of the historical working face position; The current construction location is determined based on the construction vehicle information and the construction personnel information; Obtain a preset BIM model and combine it with the station line information corresponding to the current construction location to generate the excavation section result through a three-dimensional structure matching strategy; The excavation section results are input into the engineering quantity calculation model for calculation to obtain the engineering increment. The engineering quantity calculation model is dynamically adjusted based on the work mode and environmental data of the construction personnel information. The work mode is identified through the posture change data of the smart wearable device, and the smart wearable device is associated with the construction personnel information. The project progress model is updated based on the project increment and the current construction location. The project progress model dynamically generates a progress status map through a multi-level visualization engine.

2. The method as described in claim 1, characterized in that, The step of determining the current construction location based on the construction vehicle information and the construction personnel information further includes: The location of the construction vehicle is obtained based on the construction vehicle information, and the current device location, posture change data, and operating status data of the associated smart wearable device and the construction equipment are obtained based on the construction personnel information. The operating status data is parsed to extract a first status data subset and a second status data subset, wherein the first status data subset is related to the working construction equipment, and the second status data subset is related to the moving direction of the working construction equipment; Construct a decision function, wherein the decision function is constructed based on the data duration and the combined weights of the excavation equipment; The attitude change data, the first state data subset, and the second data subset are input into the decision function to obtain the output value; When the output value exceeds the preset confidence threshold and the current device location of the smart wearable device is within the predicted construction area, and the current vehicle location of the construction vehicle is within the predicted construction area, the current device location is marked as a high confidence location. The current construction location is obtained by assisting in the verification of all the high-confidence locations.

3. The method as described in claim 2, characterized in that, The step of inputting the attitude change data, the first subset of state data, and the second subset of data into the determination function to obtain the output value includes: The posture change data is converted into a sequence of action patterns. The matching degree of the action pattern sequence is calculated by comparing it with the preset excavation operation action spectrum to obtain the action matching degree. The action matching degree is input into the determination function for correction to obtain the target determination function; The first subset of state signals and the second subset of state signals are input into the target determination function to obtain the output value.

4. The method as described in claim 2, characterized in that, The step of assisting in the verification of all the high-confidence locations to obtain the current construction location includes: Retrieve the location trajectories and signal strength of nearby smart wearable devices within the same construction period for all the aforementioned high-confidence locations; When the positioning trajectory of at least one smart wearable device in the neighboring area is stationary within the same time period, the spatiotemporal aggregation degree of personnel density and device signal strength is calculated. When the spatiotemporal aggregation degree exceeds the preset collaborative construction threshold, it is confirmed that there is a group work activity. The location with high credibility corresponding to the spatiotemporal aggregation degree is taken as the current construction location.

5. The method as described in claim 1, characterized in that, The step of obtaining a preset BIM model and generating the excavation section result by combining it with the station line information corresponding to the current construction location through a three-dimensional structure matching strategy includes: The corresponding parametric section template in the preset BIM model is retrieved based on the station line information, and the section equation corresponding to the template is obtained. The collision point set between the probe ray and the three-dimensional geometric structure data in the BIM model is obtained, wherein the probe ray is uniformly distributed in a circumferential direction with the current construction position as the origin. An implicit boundary function is fitted to the actual contour based on the set of collision points; The implicit boundary function and the section equation are non-rigidly aligned to obtain the correction parameters; The cross-sectional equation is adjusted based on the correction parameters to generate the target cross-section; Perform a Boolean difference operation between the target cross-section and the BIM model to obtain the excavated cavity; The projection of the excavated cavity in the BIM model corresponding to the current construction position is output as the excavation section result.

6. The method as described in claim 1, characterized in that, The step of inputting the excavation section result into the engineering quantity calculation model for calculation to obtain the engineering increment, wherein the engineering quantity calculation model is dynamically adjusted based on the work patterns of construction personnel and environmental data, and the work patterns of construction personnel are identified through posture change data, includes: The excavation cross-section results are discretized to generate a set of sampling points; A digital surface model of the current excavation face is formed based on the set of sampling points; Obtain the digital surface model from the previous construction cycle and calculate the spatial volume difference between the two surface models; Identify the work patterns of construction workers based on posture change data and determine the corresponding work efficiency coefficients; Environmental parameters are monitored, and environmental impact correction factors are calculated using a pre-set geotechnical mechanics model. The spatial volume difference, work efficiency coefficient, and environmental impact correction factor are input into the engineering quantity calculation model for multi-source data weighted fusion, and the engineering increment is output.

7. The method as described in claim 6, characterized in that, The step of inputting the spatial volume difference, work efficiency coefficient, and environmental impact correction factor into the engineering quantity calculation model for multi-source data weighted fusion and outputting the engineering increment includes: Calculate the information entropy values ​​of the spatial volume difference, operation efficiency coefficient, and environmental impact correction factor; The first initial weight, the second initial weight, and the third initial weight are determined based on the information entropy value. The first initial weight corresponds to the spatial volume difference, the second initial weight corresponds to the operation efficiency coefficient, and the third initial weight corresponds to the environmental impact correction factor. Monitor the stability of the rock mass and the operating status of the construction equipment at the construction site. When an abnormality is detected, dynamically adjust the first initial weight, the second initial weight, and the third initial weight. The fluctuation of the spatial volume difference, operation efficiency coefficient and environmental impact correction factor within a preset time period is calculated using time series analysis. Based on the fluctuation, the first initial weight, the second initial weight and the third initial weight are penalized or rewarded to obtain a penalty function or a reward function. The penalty function or reward function is used to optimize and adjust the first initial weight, the second initial weight, and the third initial weight to obtain the first target weight, the second target weight, and the third target weight. The weighted fusion result is obtained by multiplying the first target weight, the second target weight, and the third target weight by the spatial volume difference, the operation efficiency coefficient, and the environmental impact correction factor, respectively. The uncertainty of the weighted fusion result is corrected based on probabilistic statistical methods, and the engineering increment is output.

8. The method as described in claim 1, characterized in that, The step of updating the project progress model based on the project increment and the current construction location, and dynamically generating a progress status map based on the project progress model, includes: Establish an engineering progress model, discretize the construction site space into grid cells according to the design station number, and obtain the corresponding grid cell status. The grid cell status includes spatial coordinates, design engineering quantity, and time dimension attributes. Based on the current construction location, determine the construction grid unit, allocate the incremental engineering work to the construction grid unit according to spatial location, and obtain the actual completed engineering work volume; The expected completion time of the remaining work in a unit is calculated based on the actual completed work volume and the status of the grid unit. A multi-level progress status visualization engine is constructed to integrate the grid cell status, actual completed work volume, and expected completion time to generate a progress status map. By comparing and analyzing the progress status map and the construction plan, construction adjustment suggestions are generated.

9. A dynamic estimation device for engineering excavation progress, characterized in that, The device includes: The acquisition module is used to acquire the construction plan corresponding to the predicted construction area in order to determine the construction vehicle information and construction personnel information based on the construction plan, wherein the predicted construction area is dynamically generated based on the spatial boundary of the historical working face position. The judgment module is used to determine the current construction location based on the construction vehicle information and the construction personnel information; The matching module is used to obtain a preset BIM model and generate the excavation section result by combining the station line information corresponding to the current construction location through a three-dimensional structure matching strategy. The calculation module is used to input the excavation section results into the engineering quantity calculation model for calculation to obtain the engineering increment. The engineering quantity calculation model is dynamically adjusted based on the work mode of the construction personnel and environmental data. The work mode of the construction personnel is identified through the posture change data of the smart wearable device. The display module is used to update the project progress model based on the project increment and the current construction location. The project progress model dynamically generates a progress status map through a multi-level visualization engine.

10. A dynamic estimation device for engineering excavation progress, characterized in that, The device includes: a memory, a processor, and a tunnel excavation progress estimation program stored in the memory and running on the processor, the tunnel excavation progress estimation program being configured to implement the steps of the tunnel excavation progress estimation method as described in any one of claims 1-8.

Images