Engineering task dynamic re-planning method

Abstract

The invention discloses an engineering task dynamic re-planning method, which relates to the technical field of engineering task dynamic re-planning, and comprises the following steps: collecting equipment space coordinates, operation surface point cloud data and task completion amount in real time through multiple sensors, and calculating a progress deviation value; generating a progress thermodynamic diagram covering the construction area based on a preset engineering task digital twinborn body; performing grading response judgment according to the progress deviation value, and triggering an early warning process or a re-planning process according to a response grade; and calling the multi-objective optimization model and solving to generate a re-planning scheme when the re-planning process is triggered, performing deduction simulation based on the real-time state data of the equipment in the digital twin sand table, and outputting the predicted construction period completion degree, the cost change rate and the risk triggering probability after the re-planning scheme is executed. According to the invention, differential response of early warning and re-planning is realized by adopting a hierarchical trigger mechanism; and the precision and timeliness of construction progress monitoring and the scientificity and feasibility of scheduling decisions are improved.

Description

Technical Field

[0001] This invention relates to the field of dynamic replanning technology for engineering tasks, and in particular to a method for dynamic replanning of engineering tasks. Background Technology

[0002] In recent years, with the continuous expansion and increasing complexity of engineering construction projects, construction progress monitoring technology based on digital twins and multi-sensor fusion has gradually become a research hotspot in the industry. On the one hand, the accuracy and real-time performance of various data acquisition methods such as GNSS positioning, laser scanning, vision, and working condition sensors have been significantly improved, providing a solid hardware foundation for the three-dimensional spatial dynamic perception of construction sites. On the other hand, the synergistic development of cloud computing and edge computing architectures has made it possible to process and visualize massive amounts of spatiotemporal data in real time. Against this backdrop, researchers and engineering application departments have proposed progress assessment methods based on point cloud analysis, construction simulation platforms based on virtual reality, and full-process monitoring systems that utilize digital twins to manage construction nodes and resource allocation. These technologies have achieved certain results in improving information flow efficiency, enhancing monitoring accuracy, and promoting decision-making transparency; however, bottlenecks still need to be overcome in terms of data fusion depth, response timeliness, and decision optimization.

[0003] Existing technologies are mainly limited in the following ways: First, multi-source data fusion is mostly limited to two-dimensional or pseudo-three-dimensional visualization, which is difficult to meet the need for precise quantification of construction progress deviations in the spatial dimension; second, progress warnings are usually triggered based on a single threshold, ignoring the hierarchical correlation between deviation magnitude and system risk, and lacking differentiated strategies for responding to minor deviations or sudden large deviations; third, replanning schemes often rely on manual experience or single-objective scheduling models, ignoring the coordinated optimization of multiple factors such as delay penalties, cost increases and decreases, geological risks, and equipment idleness, making it difficult to balance the feasibility and economic benefits of the scheme; fourth, in the simulation and deduction stage, most platforms only provide static demonstrations and fail to combine real-time equipment operating conditions for dynamic simulation and risk probability prediction, making it difficult to accurately predict the actual effects after the scheme is implemented. Summary of the Invention

[0004] In view of the problems existing in a current method for dynamic replanning of engineering tasks, this invention is proposed. Therefore, the problem to be solved by this invention is how to provide a method for dynamic replanning of engineering tasks.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0006] In a first aspect, the present invention provides a method for dynamic replanning of engineering tasks, which includes: collecting equipment spatial coordinates, work surface point cloud data and task completion amount in real time by deploying multiple sensors on engineering machinery, calculating progress deviation value, and generating a progress heat map covering the construction area based on a preset digital twin of engineering tasks.

[0007] Based on the schedule deviation value, a graded response is determined, and an early warning process or a replanning process is triggered according to the response level.

[0008] When the replanning process is triggered, a multi-objective optimization model is invoked and a replanning scheme is generated. The scheme is then simulated in a digital twin sandbox based on real-time equipment status data. The predicted completion rate, cost change rate, and risk trigger probability after the replanning scheme is executed are output.

[0009] As a preferred embodiment of the dynamic replanning method for engineering tasks described in this invention, the multi-sensor includes a GNSS positioning module, a laser scanner, and an equipment condition sensor; the GNSS positioning module is used to acquire the spatial coordinates of the equipment; the laser scanner is used to acquire point cloud data of the work surface; and the equipment condition sensor is used to record the amount of task completion.

[0010] As a preferred embodiment of the dynamic replanning method for engineering tasks described in this invention, the calculation of the schedule deviation value includes:

[0011] Based on the equipment spatial coordinates, work surface point cloud data, and task completion volume, combined with the planned task volume, schedule milestones, and resource allocation scheme for each sub-region in the pre-defined digital twin, the actual progress percentage is calculated for each sub-region and expressed as follows:

[0012]

[0013] Where: η i ε represents the actual progress percentage of sub-region i. i Q represents the set of all devices performing operations within sub-region i; act,k Q represents the actual workload of equipment k during the cycle; plan,i The planned workload for sub-region i in the digital twin;

[0014] The schedule deviation value is calculated for each sub-region and expressed as follows:

[0015] Δ i =η i -η plan,i

[0016] Where: Δ i Let η be the schedule deviation value for sub-region i. plan,i This represents the percentage of the plan completed at the current point in time.

[0017] As a preferred embodiment of the dynamic replanning method for engineering tasks described in this invention, the step of generating a progress heatmap covering the construction area based on a preset digital twin of the engineering task includes:

[0018] The schedule deviation value is mapped to a predefined color gradient to generate a real-time schedule heatmap. In the 3D construction area model, each sub-area is placed with a corresponding color block according to its center coordinate position.

[0019] Draw trajectory segments on the device space coordinates of each device, with the segment colors corresponding to the device's operating status; display the progress heatmap and trajectory segments on a visualization platform.

[0020] As a preferred embodiment of the dynamic replanning method for engineering tasks described in this invention, the step of determining the graded response based on the schedule deviation value includes:

[0021] Perform continuous over-threshold detection, and define the progress deviation value of the sub-region in the t-th acquisition cycle as Δ. i Let I(t) be the indicator function for the t-th acquisition cycle. i (t) is:

[0022]

[0023] The sum of the indicator functions is calculated and expressed as:

[0024] S i (t)=I i (t)+I i (t-1)+I i (t-2)

[0025] Wherein: S i (t) is the indicator function and I for the t-th acquisition cycle. i (t-1) is the indicator function for the (t-1)th acquisition cycle, I i (t-2) is the indicator function for the (t-2)th acquisition cycle;

[0026] When S i When (t) = 3, it means that sub-region i has lagged behind by more than 10% for three consecutive cycles, triggering the subsequent process of dynamic replanning and making a graded response judgment.

[0027] At the same trigger moment, read the progress deviation value of the current collection cycle. If the progress deviation value is greater than the first limit and less than the second limit, the response level is level one, triggering the early warning process, pushing early warning information, generating a local fine-tuning plan, and notifying the on-duty engineer.

[0028] Adjusting the resource allocation of sub-region i in the digital twin is expressed as:

[0029]

[0030] in: Let i be the adjusted resource allocation for device j in sub-region i. The original planned resource allocation for device j in sub-region i; α i This is the deviation magnification factor;

[0031] If the schedule deviation exceeds the second limit, the response level is set to Level 2, triggering a replanning process. On the heatmap, all devices in spatially adjacent sub-regions with the same response level are designated as a device cluster. During the replanning period, all devices in the cluster only respond to new instructions and do not accept other temporary changes. This triggers a multi-objective optimization model to perform replanning, outputting a new global scheduling scheme. This scheme is then pushed to the command center, engineer tablets, and the cockpit. After confirmation, it replaces the original task list and is distributed to all cluster devices in real time.

[0032] As a preferred embodiment of the dynamic replanning method for engineering tasks described in this invention, the step of calling a multi-objective optimization model and solving to generate a replanning solution when the replanning process is triggered includes:

[0033] Construct a multi-objective optimization model, and set the objective function as:

[0034] minJ=ω1P delay +ω2C reset +ω3R geo +ω4L idle

[0035] Where: J is the objective function, P delay C is a penalty item for project delay. reset For the resource replacement cost item, R geo L represents the geological risk coefficient. idle For equipment idle loss, ω1, ω2, ω3, and ω4 are weighting coefficients;

[0036] The expression for the penalty for project delay is:

[0037]

[0038] Wherein: T node,i Let T be the project schedule node time for sub-region i. plan,i This represents the original planned completion time for sub-region i;

[0039] The expression for the resource replacement cost item is:

[0040]

[0041] Where: R i,j c represents the actual resource allocation for device j in sub-region i. j The unit cost required to reset the equipment;

[0042] The expression for the geological risk coefficient term is:

[0043]

[0044] Where: ρ i Let Q be the geological risk coefficient of sub-region i. act,i The actual workload of sub-region i;

[0045] The expression for the equipment idle loss term is:

[0046]

[0047] Where: t idle,k The estimated idle time for device k during the implementation of the new plan; l k Cost per unit of idle time for equipment;

[0048] The objective function is solved using a genetic algorithm or a particle swarm optimization algorithm, and the optimal solution set is output. Each solution set includes a set of actual resource allocation and project time nodes.

[0049] As a preferred embodiment of the dynamic replanning method for engineering tasks described in this invention, the step of performing simulation based on real-time equipment status data in a digital twin sandbox includes:

[0050] Each solution replaces the actual resource allocation and project timeline in the digital twin sandbox, keeping other scenario elements unchanged, and performs simulation. The simulation of each solution running in the digital twin sandbox is represented as follows:

[0051]

[0052]

[0053] Among them: Q sim,i (t+Δt) represents the progress of subregion i at time t+Δt, r i,j (t) represents the operating rate of device j in sub-region i at time t; Q sim,i (t) represents the progress of subregion i at time t, and Δt is the time step; C sim P represents the cumulative cost. risk,i This represents the probability of risk triggering.

[0054] Output evaluation metrics, calculating the predicted project completion rate, cost variation rate, and risk trigger probability for each plan, expressed as follows:

[0055]

[0056] Where: η pred,i Let C be the predicted project duration completion rate for sub-region i, and ΔC be the cost variation rate. plan For planned costs, P riskThis represents the probability of risk triggering.

[0057] The predicted completion rate, cost variation rate, and risk trigger probability of each option are presented in a table for the command center to select.

[0058] In a second aspect, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of a dynamic replanning method for an engineering task.

[0059] Thirdly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements the steps of a dynamic replanning method for an engineering task.

[0060] The beneficial effects of this invention are as follows: This method constructs a high-precision, low-latency three-dimensional progress visualization system through multi-sensor deep fusion and digital twin technology; it adopts a hierarchical triggering mechanism to realize differentiated responses to early warning and replanning; and it effectively balances the construction period, cost, and risk by utilizing multi-objective optimization and dynamic sand table simulation, significantly improving the accuracy and timeliness of construction progress monitoring, the scientificity and feasibility of scheduling decisions, and the overall benefits of on-site management. Attached Figure Description

[0061] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0062] Figure 1 This is a flowchart of a dynamic replanning method for engineering tasks. Detailed Implementation

[0063] To make the above-mentioned objects, features, and advantages of the present invention more readily understood, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0064] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0065] Secondly, the term "one embodiment" or "example" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the invention. An embodiment appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively mutually exclusive with other embodiments.

[0066] Reference Figure 1 This is the first embodiment of the present invention, which provides a dynamic replanning method for engineering tasks, including:

[0067] S1: Real-time collection of equipment spatial coordinates, work surface point cloud data and task completion amount by multiple sensors deployed on construction machinery, calculation of progress deviation value, and generation of progress heat map covering the construction area based on the preset digital twin of engineering tasks.

[0068] Specifically, the following are installed on various construction machines (such as excavators, loaders, bulldozers, etc.): GNSS positioning modules, used to obtain the real-time position of the equipment in the geographic coordinate system, i.e., the spatial coordinates of the equipment; laser scanners, used to collect point cloud data of the surrounding work surface; and equipment condition sensors (such as engine speed, oil pressure, work time timer, etc.), used to record the amount of work completed.

[0069] Latitude, longitude, and elevation data are read from the GNSS module at fixed intervals and converted into a Cartesian coordinate system for the construction site. Point cloud data: The laser scanner sampling frequency can be set to 5–10Hz. After acquiring the raw point cloud, the following processes are required: noise reduction filtering; ground segmentation (filtering out points outside the ground); and meshing processing, projecting the point cloud onto a regular two-dimensional grid for subsequent progress assessment. Task completion: Based on the working time and status recorded by the working condition sensors, the actual workload of each device is cumulatively calculated.

[0070] Input the location of the data device, the gridded point cloud, and the amount of work completed. Combine this with the planned task volume, project milestones, and resource allocation scheme for each sub-region in the pre-defined digital twin. Calculate the actual progress percentage for each sub-region, expressed as:

[0071]

[0072] Where: η i ε represents the actual progress percentage of sub-region i. i Q represents the set of all devices performing operations within sub-region i; act,k Q represents the actual workload of equipment k during the cycle; plan,i The planned workload for sub-region i in the digital twin.

[0073] The schedule deviation value is calculated for each sub-region and expressed as follows:

[0074] Δ i =η i -η plan,i

[0075] Where: Δ i Let η be the schedule deviation value for sub-region i. plan,i The percentage of the plan completed at the current time point (obtained by linear or curvilinear interpolation of the digital twin based on the project schedule nodes);

[0076] The schedule deviation value is mapped to a predefined color gradient to generate a real-time schedule heatmap. In the 3D construction area model, each sub-area is placed with a corresponding color block according to its center coordinate position.

[0077] Draw trajectory segments on the device space coordinates of each device, with the color of the segments corresponding to the device's operating status (driving, operating, standby); display the heat map and trajectory segments on a visualization platform (PC large screen, tablet, cockpit screen), and refresh automatically every 30 seconds.

[0078] S2: Based on the schedule deviation value, a graded response is determined, and an early warning process or a replanning process is triggered according to the response level;

[0079] Specifically, continuous over-threshold detection is performed, and the progress deviation value of the sub-region in the t-th acquisition cycle is defined as Δ. i (t), establish the indicator function I for the t-th acquisition cycle. i (t) is:

[0080]

[0081] The sum of the indicator functions is calculated and expressed as:

[0082] S i (t)=I i (t)+I i (t-1)+I i (t-2)

[0083] Wherein: S i (t) is the indicator function and I for the t-th acquisition cycle. i (t-1) is the indicator function for the (t-1)th acquisition cycle, I i (t-2) is the indicator function for the (t-2)th acquisition cycle;

[0084] When S i When (t) = 3, it means that sub-region i has lagged behind by more than 10% for three consecutive cycles, triggering the subsequent process of dynamic replanning and making a graded response judgment.

[0085] At the same trigger moment, the progress deviation value of the current collection cycle is read. If the progress deviation value is greater than the first limit and less than the second limit, the response level is level one, triggering the early warning process, pushing early warning information and generating a local fine-tuning plan. The early warning information includes: sub-region number; current progress deviation value and historical maximum progress deviation value; number of consecutive delayed cycles; difference between planned completion time and actual project duration; and notifying the on-duty engineer.

[0086] In a digital twin, adjustments are made only to the resource allocation near the deviation sub-region, as shown below:

[0087]

[0088] in: Let i be the adjusted resource allocation for device j in sub-region i. The original planned resource allocation for device j in sub-region i; α i This is the deviation scaling factor, which shall not exceed 10%.

[0089] It also generates a fine-tuned Gantt chart, indicating resource increases or decreases and changes in time nodes, for the on-site construction team to confirm.

[0090] If the schedule deviation exceeds the second limit, the response level is set to Level 2, triggering a replanning process. On the heatmap, all devices in spatially adjacent sub-regions with the same response level are grouped into a cluster. During the replanning period, all devices in the cluster only respond to new instructions and do not accept other temporary changes. This triggers a multi-objective optimization model for replanning, outputting a new global scheduling scheme, including: new resource allocation for each sub-region; adjusted project timelines; and a new list of device tasks and priorities. A snapshot of the global scheme is pushed to the command center, engineer tablets, and the dashboard. The command center can approve or further fine-tune the scheme, replacing the original task list upon confirmation and distributing it to all cluster devices in real time. The system continuously monitors the system; if the deviation returns to below the first limit in the next cycle, it automatically unlocks and records the return to normal status.

[0091] S3: When the replanning process is triggered, a multi-objective optimization model is invoked and a replanning scheme is generated. The scheme is then simulated in a digital twin sandbox based on real-time equipment status data. The predicted completion rate, cost change rate, and risk trigger probability after the replanning scheme is executed are output.

[0092] Specifically, a multi-objective optimization model is constructed, and the objective function is set as follows:

[0093] minJ=ω1P delay +ω2C reset +ω3R geo +ω4L idle

[0094] Where: J is the objective function, P delay C is a penalty item for project delay. reset For the resource replacement cost item, R geo L represents the geological risk coefficient. idle For equipment idle loss, ω1, ω2, ω3, and ω4 are weighting coefficients;

[0095] The expression for the penalty for project delay is:

[0096]

[0097] Wherein: T node,i Let T be the project schedule node time for sub-region i. plan,i The original planned completion time for sub-region i is denoted as ; if the actual completion time is later than the planned completion time, the difference is included in the penalty, otherwise it is not counted.

[0098] The expression for the resource replacement cost item is:

[0099]

[0100] Where: R i,j c represents the actual resource allocation for device j in sub-region i. j The unit cost required to reset the equipment.

[0101] The expression for the geological risk coefficient term is:

[0102]

[0103] Where: ρ i Let Q be the geological risk coefficient of sub-region i. act,i This represents the actual workload of sub-region i.

[0104] The expression for the equipment idle loss term is:

[0105]

[0106] Where: t idle,k The estimated idle time for device k during the implementation of the new plan; l k Cost rate per unit of equipment idle time.

[0107] The objective function is solved using multi-objective optimization solvers such as genetic algorithms or particle swarm optimization, and a representative set of optimal solutions is output. Each solution includes a set of actual resource allocations and project time nodes.

[0108] Update the current scene status in the digital twin sandbox to include: real-time spatial coordinates and operating conditions of equipment; progress of existing tasks; and geological and environmental risk distribution layers. Replace the actual resource allocation and project timelines within the digital twin sandbox for each solution, while keeping other scene elements unchanged.

[0109] The simulation was conducted, and each scheme was run in a digital twin sandbox, as shown below:

[0110]

[0111] Among them: Q sim,i (t+Δt) represents the progress of subregion i at time t+Δt, r i,j (t) represents the operating rate of device j in sub-region i at time t; Q sim,i (t) represents the progress of subregion i at time t, and Δt is the time step; C sim P represents the cumulative cost. risk,i This represents the probability of risk triggering.

[0112] Output evaluation metrics, calculating the predicted project completion rate, cost variation rate, and risk trigger probability for each plan, expressed as follows:

[0113]

[0114] Where: η pred,i Let C be the predicted project duration completion rate for sub-region i, and ΔC be the cost variation rate. plan For planned costs, P risk This represents the probability of risk triggering.

[0115] Finally, the predicted completion rate, cost variation rate, and risk trigger probability of each option will be presented in a table for the command center to select the best one.

[0116] The dynamic replanning scheme set after the sand table simulation is pushed to the command center's large screen, engineer's tablet, and equipment cockpit screen simultaneously; the command center selects equipment clusters in the heat map on the large screen by gesture and assigns new tasks in batches; the engineer's tablet receives the Gantt chart progress bar change instruction, and generates the final scheme after dragging and adjusting the task sequence; the target equipment cockpit automatically pops up a task change notification, and updates the vehicle-mounted task list after voice confirmation.

[0117] This embodiment also provides a computer device applicable to a dynamic replanning method for an engineering task, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement all or part of the steps of the method described in the above embodiments of the present invention.

[0118] This embodiment also provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, it performs the method in any optional implementation of the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0119] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0120] In summary, this method constructs a high-precision, low-latency three-dimensional progress visualization system through deep fusion of multiple sensors and digital twin technology; it adopts a hierarchical triggering mechanism to achieve differentiated responses for early warning and replanning; and it effectively balances schedule, cost, and risk by utilizing multi-objective optimization and dynamic sand table simulation, significantly improving the accuracy and timeliness of construction progress monitoring, the scientificity and feasibility of scheduling decisions, and the overall benefits of on-site management.

[0121] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A dynamic replanning method for engineering tasks, characterized in that: include, By deploying multiple sensors on construction machinery to collect equipment spatial coordinates, work surface point cloud data and task completion in real time, the progress deviation value is calculated, and a progress heat map covering the construction area is generated based on the preset digital twin of the construction task. Based on the schedule deviation value, a graded response is determined, and an early warning process or a replanning process is triggered according to the response level. When the replanning process is triggered, a multi-objective optimization model is invoked and a replanning scheme is generated. The scheme is then simulated in a digital twin sandbox based on real-time equipment status data. The predicted completion rate, cost change rate, and risk trigger probability after the replanning scheme is executed are output.

2. The dynamic replanning method for engineering tasks as described in claim 1, characterized in that: The multi-sensor system includes a GNSS positioning module, a laser scanner, and an equipment condition sensor; the GNSS positioning module is used to acquire the spatial coordinates of the equipment; the laser scanner is used to acquire point cloud data of the work surface; and the equipment condition sensor is used to record the amount of task completion.

3. The dynamic replanning method for engineering tasks as described in claim 2, characterized in that: The calculated schedule deviation value includes: Based on the equipment spatial coordinates, work surface point cloud data, and task completion volume, combined with the planned task volume, schedule milestones, and resource allocation scheme for each sub-region in the pre-defined digital twin, the actual progress percentage is calculated for each sub-region and expressed as follows: Where: η i ε represents the actual progress percentage of sub-region i. i Q represents the set of all devices performing operations within sub-region i; act,k Q represents the actual workload of equipment k during the cycle; plan,i The planned workload for sub-region i in the digital twin; The schedule deviation value is calculated for each sub-region and expressed as follows: D i =the i -or plan,i Where: Δ i Let η be the schedule deviation value for sub-region i. plan,i This represents the percentage of the plan completed at the current point in time.

4. The dynamic replanning method for engineering tasks as described in claim 3, characterized in that: The process of generating a progress heatmap covering the construction area based on a preset engineering task digital twin includes: The schedule deviation value is mapped to a predefined color gradient to generate a real-time schedule heatmap. In the 3D construction area model, each sub-area is placed with a corresponding color block according to its center coordinate position. Draw trajectory segments on the device space coordinates of each device, with the segment colors corresponding to the device's operating status; display the progress heatmap and trajectory segments on a visualization platform.

5. The dynamic replanning method for engineering tasks as described in claim 4, characterized in that: The step of determining a graded response based on the schedule deviation value includes: Perform continuous over-threshold detection, and define the progress deviation value of the sub-region in the t-th acquisition cycle as Δ. i Let I(t) be the indicator function for the t-th acquisition cycle. i (t) is: The sum of the indicator functions is calculated and expressed as: S i (t)=I i (t)+I i (t-1)+I i (t-2) Wherein: S i (t) is the indicator function and I for the t-th acquisition cycle. i (t-1) is the indicator function for the (t-1)th acquisition cycle, I i (t-2) is the indicator function for the (t-2)th acquisition cycle; When S i When (t) = 3, it means that sub-region i has lagged behind by more than 10% for three consecutive cycles, triggering the subsequent process of dynamic replanning and making a graded response judgment. At the same trigger moment, read the progress deviation value of the current collection cycle. If the progress deviation value is greater than the first limit and less than the second limit, the response level is level one, triggering the early warning process, pushing early warning information, generating a local fine-tuning plan, and notifying the on-duty engineer. Adjusting the resource allocation of sub-region i in the digital twin is expressed as: in: Let i be the adjusted resource allocation for device j in sub-region i. The original planned resource allocation for device j in sub-region i; α i This is the deviation magnification factor; If the schedule deviation exceeds the second limit, the response level is set to Level 2, triggering a replanning process. On the heatmap, all devices in spatially adjacent sub-regions with the same response level are designated as a device cluster. During the replanning period, all devices in the cluster only respond to new instructions and do not accept other temporary changes. This triggers a multi-objective optimization model to perform replanning, outputting a new global scheduling scheme. This scheme is then pushed to the command center, engineer tablets, and the cockpit. After confirmation, it replaces the original task list and is distributed to all cluster devices in real time.

6. The dynamic replanning method for engineering tasks as described in claim 5, characterized in that: The step of invoking a multi-objective optimization model and solving for a replanning solution when the replanning process is triggered includes: Construct a multi-objective optimization model, and set the objective function as: minJ=ω1P delay +ω2C reset +ω3R geo +ω4L idle Where: J is the objective function, P delay C is a penalty item for project delay. reset For the resource replacement cost item, R geo L represents the geological risk coefficient. idle For equipment idle loss, ω1, ω2, ω3, and ω4 are weighting coefficients; The expression for the penalty for project delay is: Wherein: T node,i Let T be the project schedule node time for sub-region i. plan,i This represents the original planned completion time for sub-region i; The expression for the resource replacement cost item is: Where: R i,j c represents the actual resource allocation for device j in sub-region i. j The unit cost required to reset the equipment; The expression for the geological risk coefficient term is: Where: ρ i Let Q be the geological risk coefficient of sub-region i. act,i The actual workload of sub-region i; The expression for the equipment idle loss term is: Where: t idle,k The estimated idle time for device k during the implementation of the new plan; l k Cost per unit of idle time for equipment; The objective function is solved using a genetic algorithm or a particle swarm optimization algorithm, and the optimal solution set is output. Each solution set includes a set of actual resource allocation and project time nodes.

7. The dynamic replanning method for engineering tasks as described in claim 6, characterized in that: The simulation based on real-time device status data in the digital twin sandbox includes: Each solution replaces the actual resource allocation and project timeline in the digital twin sandbox, keeping other scenario elements unchanged, and performs simulation. The simulation of each solution running in the digital twin sandbox is represented as follows: Among them: Q sim,i (t+Δt) represents the progress of subregion i at time t+Δt, r i,j (t) represents the operating rate of device j in sub-region i at time t; Q sim,i (t) represents the progress of subregion i at time t, and Δt is the time step; C sim P represents the cumulative cost. risk,i This represents the probability of risk triggering. Output evaluation metrics, calculating the predicted project completion rate, cost variation rate, and risk trigger probability for each plan, expressed as follows: Where: η pred,i Let C be the predicted project duration completion rate for sub-region i, and ΔC be the cost variation rate. plan For planned costs, P risk This represents the probability of risk triggering. The predicted completion rate, cost variation rate, and risk trigger probability of each option are presented in a table for the command center to select.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the dynamic replanning method for engineering tasks as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the dynamic replanning method for engineering tasks as described in any one of claims 1 to 7.

Images