A method, device and equipment for unmanned aerial vehicle inspection of construction procedures of a cut slope

Abstract

The present application relates to the technical field of unmanned aerial vehicle inspection, in particular to a kind of excavation slope construction process unmanned aerial vehicle inspection method, device and equipment, according to the image data and point cloud data of current construction slope periodically collected by unmanned aerial vehicle, the real-time excavation volume increment of this monitoring, newly added support area and the current un-supported new excavation surface area are obtained;According to real-time excavation volume increment, preset monitoring time interval and planned excavation speed, speed matching degree is obtained;According to the total excavation area corresponding to the newly added support area and the new excavation surface area, area coverage rate is calculated, and area matching degree is obtained;According to the exposure length of new excavation surface area and the maximum allowable exposure length of new excavation surface area, time matching degree is obtained;According to speed matching degree, area matching degree and time matching degree, the unmanned aerial vehicle inspection result of current construction slope is obtained.The fine and active prevention and control ability of slope construction process management is improved.

Description

Technical Field

[0001] This invention relates to the field of drone inspection technology, specifically to a drone inspection method, device, and equipment for excavated slope construction procedures. Background Technology

[0002] Excavation and slope protection engineering is a common and high-risk operation in the fields of highways, railways, water conservancy, and construction. The standard construction method employs a top-down, layered excavation and timely layered support cyclical operation. This means that after each layer of earth and rock is excavated to the designed outline, the fresh exposed surface of that layer must be immediately supported. Only after the support structure of that layer is stable can the next layer be excavated. This excavation-support-re-excavation work chain requires extremely high precision in the coordination of procedures.

[0003] However, in actual engineering management, the control over the tightness of process connections has long faced the following technical bottlenecks, leading to frequent risks such as delayed support, over-excavation, and insufficient structural strength, seriously threatening construction safety and project progress. Traditional management relies on manual inspections and construction log records, which cannot accurately and in real time obtain precise spatiotemporal information on when excavation is completed and when support begins for each specific area. The exposure time of the free face between the two key processes of excavation and support cannot be accurately measured and monitored, while slope stability decreases non-linearly with exposure time. This has resulted in the core risk of delayed support being managed through experience-based judgment and post-event discovery for a long time. Summary of the Invention

[0004] The purpose of this invention is to provide a method, device, and equipment for unmanned aerial vehicle (UAV) inspection of excavated slope construction processes, which solves the problems in the prior art.

[0005] This invention is achieved through the following technical solution:

[0006] In a first aspect, embodiments of the present invention provide a method for unmanned aerial vehicle (UAV) inspection of excavated slope construction procedures, including:

[0007] Based on the image data and point cloud data of the current construction slope collected regularly by drones, the real-time excavation volume increment, newly added support area, and currently unsupported new excavation surface area are obtained in this monitoring.

[0008] Based on the real-time excavation volume increment, the preset monitoring time interval, and the planned excavation speed, a speed matching degree, which characterizes the degree to which the construction progress conforms to the plan, is obtained.

[0009] Based on the newly added support area and the newly excavated area, the area coverage rate is calculated to obtain the area matching degree, which characterizes the timeliness of support follow-up.

[0010] Based on the exposure time of the newly excavated face area and the maximum allowable exposure time of the newly excavated face area, a time matching degree characterizing the tightness of process connection is obtained;

[0011] The drone inspection results of the current construction slope are obtained based on the speed matching degree, the area matching degree, and the time matching degree.

[0012] Preferably, the step of obtaining the real-time excavation volume increment, newly added support area, and currently unsupported new excavation surface area based on the image data and point cloud data of the current construction slope collected periodically by the UAV includes:

[0013] A current 3D terrain model is generated based on point cloud data of the current construction slope collected periodically by drones.

[0014] The current three-dimensional terrain model is compared with the preset design model to determine whether the deviation of the actual excavation area from the designed excavation area is within the allowable error range.

[0015] If the deviation of the actual excavation area from the designed excavation area is within the allowable error range, the current three-dimensional terrain model is compared with the historical three-dimensional terrain model obtained from the last monitoring within the actual excavation area to obtain the real-time excavation volume increment.

[0016] Computer vision analysis was performed on the image data obtained from this monitoring to obtain the current support area with support structure characteristics;

[0017] If the current support area and the actual excavation area belong to the same layer in the design model, then the current support area is compared with the historical support area obtained from the last monitoring to obtain the newly added support area and the newly added support area of ​​the newly added support area.

[0018] The area outside the current support area within the actual excavation area is defined as the newly excavated face area that is currently unsupported.

[0019] Preferably, the method further includes:

[0020] If the deviation of the actual excavation area from the designed excavation area is not within the allowable error range, an over-excavation warning message will be generated and the over-excavation area will be identified.

[0021] Preferably, the method further includes:

[0022] If the current support area and the actual excavation area do not belong to the same layer in the design model, then the latest support completion time of the current support area is obtained from the acquisition time series of the image data;

[0023] The actual maintenance time is calculated based on the latest support completion time and the current time.

[0024] The minimum curing time is determined based on the type of support material in the current support area;

[0025] If the actual maintenance time is less than the minimum maintenance time, then an insufficient support strength warning is generated based on the location information of the current support area and the maintenance shortage time.

[0026] Preferably, the step of obtaining the speed matching degree, which characterizes the degree of conformity between the construction progress and the plan, based on the real-time excavation volume increment, the preset monitoring time interval, and the planned excavation speed, includes:

[0027] The actual average excavation speed is calculated based on the real-time excavation volume increment and the monitoring time interval.

[0028] The speed ratio is obtained based on the actual average excavation speed and the planned excavation speed;

[0029] The speed ratio is converted into a speed matching degree between 0 and 1 using a preset first mapping function.

[0030] Preferably, the step of obtaining the time matching degree characterizing the tightness of process connection based on the exposure time of the newly excavated face area and the maximum allowable exposure time of the newly excavated face area includes:

[0031] Based on the acquisition time series of the image data, the first appearance time of the newly excavated face area is identified, and the exposure duration is calculated according to the current time;

[0032] Based on the soil and rock type of the newly excavated area, the maximum allowable exposure time is obtained by consulting the preset exposure time risk comparison table.

[0033] The exposure ratio is obtained based on the ratio of the exposure duration to the maximum allowable exposure duration;

[0034] The exposure ratio is converted into a time matching degree between 0 and 1 using a preset second mapping function.

[0035] Preferably, obtaining the UAV inspection results of the current construction slope based on the speed matching degree, the area matching degree, and the time matching degree includes:

[0036] Obtain the current environmental parameters that affect construction safety, including at least the current meteorological conditions and geological risk level;

[0037] Based on the environmental parameters, dynamic weights are assigned to the velocity matching degree, area matching degree, and time matching degree, respectively.

[0038] The drone inspection results are obtained by performing a weighted summation based on the speed matching degree, area matching degree, time matching degree and their respective dynamic weights.

[0039] Preferably, the method further includes:

[0040] The construction risk level is determined based on the threshold range in which the drone inspection results fall;

[0041] Identify the lowest value among the velocity matching degree, area matching degree, and time matching degree;

[0042] Based on a pre-defined decision rule base, the combination of the construction risk level and the minimum value item is used as input conditions to match and output at least one basic intervention measure.

[0043] Secondly, embodiments of the present invention provide a drone inspection device for excavated slope construction procedures, comprising:

[0044] The data acquisition module is used to obtain the real-time excavation volume increment, newly added support area, and currently unsupported new excavation surface area based on the image data and point cloud data of the current construction slope collected periodically by the UAV.

[0045] The speed matching module is used to obtain the speed matching degree, which represents the degree of conformity between the construction progress and the plan, based on the real-time excavation volume increment, the preset monitoring time interval and the planned excavation speed.

[0046] The area matching module is used to calculate the area coverage rate based on the newly added support area and the newly excavated surface area, and obtain the area matching degree that characterizes the timeliness of support follow-up.

[0047] The time matching module is used to obtain the time matching degree, which characterizes the tightness of the process connection, based on the exposure time of the newly excavated face area and the maximum allowable exposure time of the newly excavated face area.

[0048] The evaluation result module is used to obtain the UAV inspection results of the current construction slope based on the speed matching degree, the area matching degree, and the time matching degree.

[0049] Thirdly, embodiments of the present invention provide an electronic device, including: at least one processor, at least one memory, and computer program instructions stored in the memory, which, when executed by the processor, implement the method of the first aspect described above.

[0050] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0051] By efficiently acquiring high-resolution images and laser point cloud data through a drone platform, and based on 3D model difference and computer vision analysis, the system achieves automated and high-precision extraction of excavation volume increment, support area change and unsupported area, solving the problems of low efficiency, incomplete coverage and difficulty in data quantification of manual inspection.

[0052] By introducing matching indices across three dimensions—speed, area, and time—a multi-dimensional quantitative evaluation model for process collaboration was constructed. Calculating the speed matching degree transforms construction progress management from experience-based judgment to rate comparison based on measured data, identifying risks of being ahead of schedule or behind schedule. Calculating the area matching degree converts the completion status of support work into a quantitative expression of spatial coverage, intuitively reflecting the degree of spatial lag in support work. By introducing the concepts of exposure time and maximum permissible exposure time and calculating the time matching degree, the time risk of support lag is transformed into a quantifiable and comparable numerical indicator.

[0053] By comprehensively analyzing the matching degree across three dimensions, a holistic drone inspection result is output. This reflects the coordination status and potential disconnect risks of the two key processes of excavation and support in terms of progress, space, and time. It provides directly verifiable data support for dynamic construction control and proactive risk management, enhancing the precision and proactive prevention capabilities of slope construction process management. Attached Figure Description

[0054] To more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of the present invention and should not be considered as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort. In the drawings:

[0055] Figure 1 This is a flowchart illustrating the UAV inspection method for excavated slope construction processes provided by the present invention.

[0056] Figure 2 This is a schematic diagram of the unmanned aerial vehicle (UAV) inspection device for excavated slope construction processes provided by the present invention.

[0057] Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the embodiments and accompanying drawings. The illustrative embodiments and descriptions of the present invention are only used to explain the present invention and are not intended to limit the present invention.

[0059] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0060] It should be noted that all actions involving the acquisition of signals, information, or data in this invention are carried out in compliance with the relevant data protection laws and regulations of the locality and with authorization from the owner of the relevant device.

[0061] Example 1

[0062] Please see Figure 1 This invention provides a method for unmanned aerial vehicle (UAV) inspection of excavated slope construction procedures, including:

[0063] S1. Based on the image data and point cloud data of the current construction slope collected regularly by the UAV, the real-time excavation volume increment, newly added support area and the currently unsupported new excavation surface area are obtained in this monitoring.

[0064] Specifically, based on image data and point cloud data of the current construction slope collected periodically by drones, the point cloud data is a dense set of points reflecting the three-dimensional spatial coordinates of the ground surface, obtained by lidar scanning. By performing a three-dimensional model difference calculation between the point cloud data acquired in this monitoring and the point cloud data acquired in the previous monitoring, the volume of earth and rock removed during the two monitoring intervals is obtained, i.e., the real-time excavation volume increment. Simultaneously, image segmentation processing is performed on the currently collected image data to identify areas with visual characteristics of the support material (e.g., color, texture, and regular shape distinguishing them from the original soil and rock). The total area is calculated, and the area of ​​the support area already identified in the previous monitoring is subtracted to obtain the newly added support area. Areas within the entire currently monitored excavation range that do not belong to the aforementioned identified support areas are defined as the newly excavated, unsupported surface areas. This step, through automated data processing, achieves dynamic and quantitative perception of the excavation volume and support completion volume during construction.

[0065] S2. Based on the real-time excavation volume increment, the preset monitoring time interval, and the planned excavation speed, obtain the speed matching degree, which characterizes the degree of conformity between the construction progress and the plan;

[0066] Specifically, the actual average excavation speed is calculated by dividing the real-time excavation volume increment obtained in step S1 by a preset monitoring time interval, where the monitoring time interval is a fixed duration between two UAV data acquisitions. The actual average excavation speed is then compared with the planned excavation speed predetermined in the construction organization design. The speed matching degree is obtained by calculating the ratio or setting a functional relationship between the two. This index reflects the consistency between the actual construction pace and the planned pace; when the actual speed matches the planned speed, the value approaches 1; when it is ahead, it is greater than 1; and when it lags behind, it is less than 1. This calculation transforms construction progress management from qualitative judgment to quantitative evaluation based on measured data.

[0067] S3. Based on the newly added support area and the newly excavated area, calculate the area coverage rate to obtain the area matching degree that characterizes the timeliness of support follow-up.

[0068] Specifically, the newly added support area is divided by the area of ​​the newly excavated face to obtain the area coverage rate, which is the area matching degree. This calculation directly quantifies the proportion of the newly formed excavated free face that receives immediate support at the current point in time. The higher this value, the more timely and complete the support work is in terms of spatial follow-up.

[0069] S4. Based on the exposure time of the newly excavated face area and the maximum allowable exposure time of the newly excavated face area, obtain the time matching degree that characterizes the tightness of the process connection;

[0070] Specifically, the exposure duration refers to the length of time elapsed from when the newly excavated area is first identified as excavated in the monitoring data to the current monitoring time. The maximum allowable exposure duration is the upper limit of the time during which the area can be safely exposed without support, determined through stability analysis based on the engineering geological characteristics of the soil and rock mass (such as cohesion and internal friction angle) and environmental conditions. The exposure duration is compared with the maximum allowable exposure duration, and the time matching degree is calculated using a preset function (such as a linear decay function or an exponential decay function). This indicator assesses the time risk of the newly excavated face being in an unprotected state; the longer the exposure time and the closer it is to the safety limit, the lower this value.

[0071] S5. Based on the speed matching degree, the area matching degree, and the time matching degree, obtain the UAV inspection results of the current construction slope.

[0072] Specifically, the velocity matching degree, area matching degree, and time matching degree calculated in steps S2, S3, and S4 are integrated using a weighted summation or rule-based fusion method to obtain the UAV inspection result. This result is a comprehensive quantitative indicator used to evaluate the coordination level of the two key processes of excavation and support in three dimensions: schedule rhythm, spatial coverage, and temporal sequence. This integrated assessment can more comprehensively reveal the systemic risks in process connection and provide clear data basis for optimizing construction organization.

[0073] In some implementation methods, S1, based on image data and point cloud data of the current construction slope collected periodically by the UAV, obtains the real-time excavation volume increment, newly added support area, and currently unsupported newly excavated surface area, including:

[0074] S11. Generate the current three-dimensional terrain model based on the point cloud data of the current construction slope collected periodically by the UAV;

[0075] Specifically, by using the point cloud data as input, a 3D reconstruction algorithm (such as triangulation or Poisson reconstruction) is employed to generate a continuous surface model that reflects the terrain's undulations—the current 3D terrain model. This model serves as the foundational digital carrier for all subsequent spatial analysis and quantitative calculations, and its accuracy directly determines the reliability of the analysis. Through this step, discrete measurement data is transformed into a structured 3D representation that can be used by computers for spatial computation and recognition.

[0076] S12. Compare the current three-dimensional terrain model with the preset design model to determine whether the deviation of the actual excavation area from the designed excavation area is within the allowable error range.

[0077] Specifically, the preset design model is a three-dimensional digital model representing the final design form of the slope, established based on the construction drawings. After spatially registering the current three-dimensional terrain model generated in S11 with the design model in the same coordinate system, the spatial positional differences between the two are calculated to determine whether there is a deviation between the actual excavation surface (i.e., the actual excavation area) and the excavation range specified in the design (i.e., the design excavation area), and whether the deviation is within the allowable error range set according to construction specifications or design requirements. This step realizes the digital verification of the construction outline, ensuring that subsequent analysis is carried out under the premise of meeting design requirements, thereby excluding illegal over-excavation and other operations from the analysis process, and enhancing the engineering significance and decision-making value of the analysis results.

[0078] S13. If the deviation of the actual excavation area from the designed excavation area is within the allowable error range, the current three-dimensional terrain model is compared with the historical three-dimensional terrain model obtained from the last monitoring within the actual excavation area to obtain the real-time excavation volume increment.

[0079] Specifically, if the deviation determined in S12 is within the allowable range, the current 3D terrain model generated in S11 is overlaid and compared with the historical 3D terrain model generated and stored in the previous monitoring within the spatial range defined by the actual excavation area that has passed the verification. By performing differential calculations on the elevation or volume of the two 3D models at the same spatial location, the volume of earth and rock removed in this area since the last monitoring is obtained, i.e., the real-time excavation volume increment. This increment is a core quantitative indicator reflecting the construction progress over a period of time, and the regional constraints of its calculation ensure that the data comes only from compliant excavation work faces, avoiding data distortion caused by over-excavation.

[0080] S14. Perform computer vision analysis on the image data obtained from this monitoring to obtain the current support area with support structure characteristics;

[0081] Specifically, the image data acquired during this monitoring was analyzed using image processing and pattern recognition methods. By extracting areas in the images that differ significantly from the surrounding original soil and rock in color, texture, or edge features, and then using predefined visual feature templates for support structures or machine learning models to identify areas where support construction has been completed, these areas are designated as the current support zones. This step automatically extracts semantic information related to the engineering structure from two-dimensional images, transforming visual data into locatable and measurable spatial objects.

[0082] S15. If the current support area and the actual excavation area belong to the same layer in the design model, then the current support area is compared with the historical support area obtained from the last monitoring to obtain the newly added support area and the newly added support area of ​​the newly added support area.

[0083] Specifically, firstly, the current support area identified in S14 is mapped to the design model, and it is determined whether it belongs to the same construction layer defined in the design model as the actual excavation area described in S13. If they belong to the same layer, the current support area is then compared with the historical support area identified and stored during the last monitoring under the same spatial reference system. Through spatial geometric operations, areas newly appearing in this monitoring, i.e., areas that were only supported after the last monitoring, are identified and defined as newly added support areas. The surface area of ​​these newly added areas is then calculated as the newly added support area. This step, by introducing layer attribution judgment and time sequence comparison, ensures that the statistics of support area are performed within the correct construction logic level.

[0084] S16. The area outside the current support area within the actual excavation area is defined as the new unsupported excavation face area.

[0085] Specifically, the actual excavated area defined in S12 and verified as qualified is taken as the total scope to be analyzed. From this total scope, Boolean difference operation is used to subtract the space occupied by the currently supported area identified in S14. The remaining space is determined as the currently unsupported new excavation face area. This area represents the slope free face that has been excavated according to the design but has not yet been structurally protected at the current moment.

[0086] In some implementations, if the deviation of the actual excavation area from the designed excavation area is not within the allowable error range, an over-excavation warning message is generated and the over-excavation area is identified.

[0087] Specifically, if the comparison result in step S12 determines that the deviation between the actual excavation area and the designed excavation area exceeds the allowable error range, the system automatically triggers the early warning generation process. Here, the deviation refers to the spatial positional difference between the actual excavated three-dimensional surface and the corresponding surface in the design model. This difference may manifest as the excavation area being vertically deeper than intended. Based on the three-dimensional difference calculation results, the system will generate early warning information containing quantitative data such as the location, volume, and depth of the over-excavation. This information is presented in the form of a structured alarm message. Simultaneously, the system will graphically mark the specific spatial range of the over-excavation on the current three-dimensional terrain model or associated digital construction drawings, using highlight filling, boundary delineation, or numerical annotation. This marked area is the over-excavation area. This step achieves automatic identification, quantitative assessment, and visual positioning of construction violations, transforming the significant safety hazard of over-excavation from traditional post-event review to real-time detection and precise warning, directly intervening in the construction process to meet design safety boundaries.

[0088] In some implementations, if the current support area and the actual excavation area do not belong to the same layer in the design model, the latest support completion time of the current support area is obtained from the acquisition time series of the image data.

[0089] The actual maintenance time is calculated based on the latest support completion time and the current time.

[0090] The minimum curing time is determined based on the type of support material in the current support area;

[0091] If the actual maintenance time is less than the minimum maintenance time, then an insufficient support strength warning is generated based on the location information of the current support area and the maintenance shortage time.

[0092] Specifically, if the judgment result in step S15 is that the current support area and the actual excavation area do not belong to the same construction layer in the design model, it indicates that the currently monitored support operation may not be for the latest excavation face, but rather a supplement or repair to an earlier formed upper layer or an earlier construction section. Under this logical premise, the system will trace the historical monitoring data related to the area. Specifically, it will analyze and determine the moment when the support area first appears visually complete and has not changed since then, from the image data acquisition sequence stored in chronological order. This moment is determined as the latest support completion time. The difference between the current system time and the latest support completion time is the actual curing time experienced by the support area since construction was completed. Further, the system calls the preset engineering database based on the support material type of the area. The database stores the shortest time required for different types of support materials (such as ordinary cement mortar, early-strength concrete, and sprayed synthetic fiber concrete) to develop their strength under standard environmental conditions to safely withstand the excavation disturbance or design load of the next layer. This time is defined as the minimum curing time.

[0093] Finally, the calculated actual curing time is compared with the minimum curing time determined by the query. If the actual curing time is less than the minimum curing time, it is determined that the support structure at that location does not yet have sufficient strength to withstand the risks that may arise from subsequent construction activities. The system then generates an early warning message, which integrates at least the spatial coordinates of the current support area (or its chainage range in the construction drawing) and the curing shortage time calculated based on the difference between the two. This early warning message aims to remind managers that disturbing operations such as excavation should be avoided beneath the support structure in the designated area until it reaches sufficient strength. This step achieves indirect, non-contact monitoring and early warning of the support structure strength formation process, preventing the risk of support structure failure due to insufficient curing time through time-series analysis and rule-based judgment.

[0094] In some implementations, S2, based on the real-time excavation volume increment, the preset monitoring time interval, and the planned excavation speed, obtains a speed matching degree characterizing the degree of conformity between the construction progress and the plan, including:

[0095] The actual average excavation speed is calculated based on the real-time excavation volume increment and the monitoring time interval.

[0096] The speed ratio is obtained based on the actual average excavation speed and the planned excavation speed;

[0097] The speed ratio is converted into a speed matching degree between 0 and 1 using a preset first mapping function.

[0098] Specifically, the first mapping function can be a piecewise exponential function:

[0099] ;

[0100] in, For speed matching degree, The ratio of speeds, For slope adjustment parameters, such as .

[0101] If a slope is planned to be excavated at a rate of 800 cubic meters per day, but drone monitoring shows an actual daily excavation rate of 1000 cubic meters over the past two days, the actual speed is 1.25 times the planned rate. The system does not directly use this ratio, but instead converts it into a score between 0 and 1 using a preset mapping rule. This rule reflects engineering management experience: excessively fast progress may lead to insufficient support work or strained resource chains. Therefore, excessively fast progress exceeding a reasonable threshold will not receive a high score; its matching degree will decrease from the ideal value of 1.0 to approximately 0.7, thus warning of potential collaborative risks despite ahead-of-time progress. Conversely, excessively slow progress will also lead to a lower score. The final generated speed matching degree is a composite indicator that integrates progress efficiency and collaborative safety, aiming to quantify the health of the construction rhythm rather than simply measuring speed.

[0102] In some implementations, S4, based on the exposure time of the newly excavated face area and the maximum allowable exposure time of the newly excavated face area, obtains a time matching degree characterizing the tightness of the process connection, including:

[0103] Based on the acquisition time series of the image data, the first appearance time of the newly excavated face area is identified, and the exposure duration is calculated according to the current time;

[0104] Based on the soil and rock type of the newly excavated area, the maximum allowable exposure time is obtained by consulting the preset exposure time risk comparison table.

[0105] The exposure ratio is obtained based on the ratio of the exposure duration to the maximum allowable exposure duration;

[0106] The exposure ratio is converted into a time matching degree between 0 and 1 using a preset second mapping function.

[0107] Specifically, this step assesses the temporal connection between the support and excavation processes by quantifying the time risk of the newly excavated face being unprotected. First, based on a chronologically stored sequence of image data, frame-by-frame comparison and target area identification determine the moment the newly excavated face area was first clearly observed in monitoring history—the first appearance time. The difference between this moment and the current processing time represents the duration of continuous exposure for that area, directly related to the strength decay of the slope's soil and rock mass due to stress release, weathering, or softening upon contact with water. To determine if this exposure duration is safe, the system queries a pre-generated exposure duration risk comparison table based on previous geological survey data or the soil and rock mass type determined by image features. This table integrates geotechnical parameters, engineering experience, and regulatory recommendations, specifying the maximum permissible exposure duration for each type of soil and rock mass to maintain basic stability under typical working conditions. The calculated actual exposure duration is divided by the retrieved maximum permissible exposure duration to obtain the exposure ratio. This ratio intuitively reflects how close the current exposure state is to the safety limit; a higher ratio indicates a more severe accumulation of risk. Finally, to make this ratio applicable to multi-dimensional comprehensive assessments, it needs to be transformed into a standard range of 0 to 1 using a pre-defined second mapping function. The transformed value is the time matching degree. Similar to the velocity matching degree function, this second mapping function is also non-linear: when the exposure ratio is low (much less than 1), the time matching degree value is high and changes gradually, indicating that the risk is controllable; when the exposure ratio approaches or exceeds 1, the function will cause its mapping value to drop sharply and approach 0, warning that support is severely lagging and the risk of instability has increased sharply. Through this step, the time risk of support lag is transformed from a qualitative description into a calculable, comparable, and dynamically reflective quantitative indicator of non-linear risk growth, providing clear data basis for prioritizing high-risk areas.

[0108] In some implementations, S5, based on the speed matching degree, the area matching degree, and the time matching degree, obtains the UAV inspection results of the current construction slope, including:

[0109] S51. Obtain the current environmental parameters that affect construction safety. The environmental parameters shall include at least the current meteorological conditions and geological risk level.

[0110] Specifically, the environmental parameters include at least: current meteorological conditions, the specific data of which can be obtained from on-site meteorological stations or meteorological service interfaces, and are usually quantified as factors that directly affect slope stability, such as rainfall intensity, duration of continuous rainfall, and temperature; and geological risk level, which is a macroscopic classification characterizing the stability of the soil and rock mass in the current work area, based on a comprehensive judgment of the geological conditions revealed by the preliminary investigation report, construction, and real-time monitoring displacement data. These environmental parameters together constitute the assessment background.

[0111] S52. Based on the environmental parameters, assign dynamic weights to the speed matching degree, area matching degree, and time matching degree respectively;

[0112] Specifically, based on the acquired environmental parameters, the system calculates and assigns dynamic weights to velocity matching degree, area matching degree, and time matching degree through preset weight decision rules. These weight decision rules consist of a series of conditional logics. For example, during periods of continuous rainfall or increased geological risk, the weight of time matching degree is significantly increased because the risk of prolonged exposure is dramatically amplified in adverse environments. Conversely, when geological conditions are favorable and weather is stable, the weight of velocity matching degree may be appropriately increased to focus on construction efficiency. The weight allocation must satisfy a normalization constraint, meaning the sum of the weights of the three factors must be 1. This dynamic adjustment mechanism ensures that the assessment model can adapt to changes in external conditions, keeping the assessment focus on the most critical risk dimension at any given time.

[0113] S53. Based on the speed matching degree, area matching degree, time matching degree and their respective dynamic weights, perform weighted summation calculation to obtain the UAV inspection result.

[0114] Specifically, the system performs a weighted summation calculation, which involves multiplying the speed matching degree by its corresponding dynamic weight, adding the area matching degree by its corresponding dynamic weight, and adding the time matching degree by its corresponding dynamic weight. The sum of these three is the final UAV inspection result. This result is a comprehensive evaluation value between 0 and 1, and its value generally represents the degree of coordination and health of the excavation and support processes in terms of progress, spatial coverage, and temporal sequence under the current environmental conditions. Low scores indicate serious process disconnects or construction in a high-risk environment, while high scores indicate good process coordination or controllable environmental risks. By introducing environmental parameters and dynamic weights, this comprehensive evaluation result overcomes the limitations of static evaluation, considers the real-time environment, and improves the accuracy of the evaluation.

[0115] In some embodiments, the method further includes:

[0116] The construction risk level is determined based on the threshold range in which the drone inspection results fall;

[0117] Identify the lowest value among the velocity matching degree, area matching degree, and time matching degree;

[0118] Based on a pre-defined decision rule base, the combination of the construction risk level and the minimum value item is used as input conditions to match and output at least one basic intervention measure.

[0119] Specifically, the calculated drone inspection results are first compared with multiple preset threshold ranges to determine the corresponding construction risk level. For example, a level between 0.8 and 1.0 is defined as low risk, between 0.6 and 0.8 as medium risk, and below 0.6 as high risk. This grading maps continuous assessment values ​​to discrete risk states, facilitating hierarchical management and response. While determining the overall risk level, the system analyzes three sub-indicators in parallel, identifying the lowest value among speed matching, area matching, and time matching – the minimum value. This represents the weakest link in the current process coordination; for example, if the time matching is lowest, the main problem is delayed support; if the area matching is lowest, the main problem is insufficient support coverage. Then, the construction risk level and the minimum value are used as input to query a preset decision rule base. This rule base is a predefined set of condition-measure mappings based on expert experience and engineering logic. For example, a rule could be defined as follows: if the risk level is medium and the minimum value is time matching, then the output measure is: conduct more frequent patrols of the exposed area and prepare emergency support materials. The system automatically outputs one or more basic intervention measures most relevant to the specific risk situation through matching. This process automates the process from data diagnosis to solution recommendation, providing accurate and timely decision support for on-site managers.

[0120] Example 2

[0121] Please see Figure 2 This invention provides a drone inspection device for excavated slope construction procedures, comprising:

[0122] The data acquisition module is used to obtain the real-time excavation volume increment, newly added support area, and currently unsupported new excavation surface area based on the image data and point cloud data of the current construction slope collected periodically by the UAV.

[0123] The speed matching module is used to obtain the speed matching degree, which represents the degree of conformity between the construction progress and the plan, based on the real-time excavation volume increment, the preset monitoring time interval and the planned excavation speed.

[0124] The area matching module is used to calculate the area coverage rate based on the newly added support area and the newly excavated surface area, and obtain the area matching degree that characterizes the timeliness of support follow-up.

[0125] The time matching module is used to obtain the time matching degree, which characterizes the tightness of the process connection, based on the exposure time of the newly excavated face area and the maximum allowable exposure time of the newly excavated face area.

[0126] The evaluation result module is used to obtain the UAV inspection results of the current construction slope based on the speed matching degree, the area matching degree, and the time matching degree.

[0127] It should be noted that each module and unit in the UAV inspection device for excavated slope construction process in this embodiment corresponds one-to-one with each step in the UAV inspection method for excavated slope construction process in the aforementioned embodiment. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned UAV inspection method for excavated slope construction process, and will not be repeated here.

[0128] Example 3

[0129] Please see Figure 3 This embodiment provides an electronic device, including at least one processor 301 and a memory 302. Optionally, the device further includes a communication component 303. The processor 301, memory 302, and communication component 303 are connected via a bus 304.

[0130] In a specific implementation, at least one processor 301 executes computer execution instructions stored in memory 302, causing at least one processor 301 to perform the above-described method.

[0131] The specific implementation process of processor 301 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0132] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0133] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0134] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0135] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0136] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0137] The aforementioned readable 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 read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0138] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0139] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0140] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0141] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0142] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0143] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0144] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for unmanned aerial vehicle (UAV) inspection of excavated slope construction procedures, characterized in that, include: Based on the image data and point cloud data of the current construction slope collected regularly by drones, the real-time excavation volume increment, newly added support area, and currently unsupported new excavation surface area are obtained in this monitoring. Based on the real-time excavation volume increment, the preset monitoring time interval, and the planned excavation speed, a speed matching degree, which characterizes the degree to which the construction progress conforms to the plan, is obtained. Based on the newly added support area and the newly excavated area, the area coverage rate is calculated to obtain the area matching degree, which characterizes the timeliness of support follow-up. The exposure time of the newly excavated face area is compared with the maximum allowable exposure time of the newly excavated face area. The time matching degree, which characterizes the tightness of the process connection, is calculated by a preset function. The preset function is a linear decay function or an exponential decay function. The drone inspection results of the current construction slope are obtained based on the speed matching degree, the area matching degree, and the time matching degree. The process of obtaining a speed matching degree, which characterizes the degree of conformity between the construction progress and the plan, based on the real-time excavation volume increment, the preset monitoring time interval, and the planned excavation speed, includes: The actual average excavation speed is calculated based on the real-time excavation volume increment and the monitoring time interval. The speed ratio is obtained based on the actual average excavation speed and the planned excavation speed; The speed ratio is converted into a speed matching degree between 0 and 1 using a preset first mapping function.

2. The method for unmanned aerial vehicle (UAV) inspection of excavated slope construction procedures according to claim 1, characterized in that, The method, based on image and point cloud data of the current construction slope collected periodically by drones, obtains the real-time excavation volume increment, newly added support area, and currently unsupported newly excavated surface area, including: A current 3D terrain model is generated based on point cloud data of the current construction slope collected periodically by drones. The current three-dimensional terrain model is compared with the preset design model to determine whether the deviation of the actual excavation area from the designed excavation area is within the allowable error range. If the deviation of the actual excavation area from the designed excavation area is within the allowable error range, the current three-dimensional terrain model is compared with the historical three-dimensional terrain model obtained from the last monitoring within the actual excavation area to obtain the real-time excavation volume increment. Computer vision analysis was performed on the image data obtained from this monitoring to obtain the current support area with support structure characteristics; If the current support area and the actual excavation area belong to the same layer in the design model, then the current support area is compared with the historical support area obtained from the last monitoring to obtain the newly added support area and the newly added support area of ​​the newly added support area. The area outside the current support area within the actual excavation area is defined as the newly excavated face area that is currently unsupported.

3. The method for unmanned aerial vehicle (UAV) inspection of excavated slope construction procedures according to claim 2, characterized in that, The method further includes: If the deviation of the actual excavation area from the designed excavation area is not within the allowable error range, an over-excavation warning message will be generated and the over-excavation area will be identified.

4. The method for unmanned aerial vehicle (UAV) inspection of excavated slope construction procedures according to claim 2, characterized in that, The method further includes: If the current support area and the actual excavation area do not belong to the same layer in the design model, then the latest support completion time of the current support area is obtained from the acquisition time series of the image data; The actual maintenance time is calculated based on the latest support completion time and the current time. The minimum curing time is determined based on the type of support material in the current support area; If the actual maintenance time is less than the minimum maintenance time, then an insufficient support strength warning is generated based on the location information of the current support area and the maintenance shortage time.

5. A method for unmanned aerial vehicle (UAV) inspection of excavated slope construction procedures according to claim 1, characterized in that, The process of obtaining a time matching degree characterizing the tightness of process connections based on the exposure time of the newly excavated face area and the maximum allowable exposure time of the newly excavated face area includes: Based on the acquisition time series of the image data, the first appearance time of the newly excavated face area is identified, and the exposure duration is calculated according to the current time; Based on the soil and rock type of the newly excavated area, the maximum allowable exposure time is obtained by consulting the preset exposure time risk comparison table. The exposure ratio is obtained based on the ratio of the exposure duration to the maximum allowable exposure duration; The exposure ratio is converted into a time matching degree between 0 and 1 using a preset second mapping function.

6. A method for unmanned aerial vehicle (UAV) inspection of excavated slope construction procedures according to claim 1, characterized in that, The process of obtaining the UAV inspection results of the current construction slope based on the speed matching degree, the area matching degree, and the time matching degree includes: Obtain the current environmental parameters that affect construction safety, including at least the current meteorological conditions and geological risk level; Based on the environmental parameters, dynamic weights are assigned to the velocity matching degree, area matching degree, and time matching degree, respectively. The drone inspection results are obtained by performing a weighted summation based on the speed matching degree, area matching degree, time matching degree and their respective dynamic weights.

7. A method for unmanned aerial vehicle (UAV) inspection of excavated slope construction procedures according to claim 1, characterized in that, The method further includes: The construction risk level is determined based on the threshold range in which the drone inspection results fall; Identify the lowest value among the velocity matching degree, area matching degree, and time matching degree; Based on a pre-defined decision rule base, the combination of the construction risk level and the minimum value item is used as input conditions to match and output at least one basic intervention measure.

8. A drone inspection device for excavated slope construction procedures, characterized in that, include: The data acquisition module is used to obtain the real-time excavation volume increment, newly added support area, and currently unsupported new excavation surface area based on the image data and point cloud data of the current construction slope collected periodically by the UAV. The speed matching module is used to obtain the speed matching degree, which represents the degree of conformity between the construction progress and the plan, based on the real-time excavation volume increment, the preset monitoring time interval and the planned excavation speed. The area matching module is used to calculate the area coverage rate based on the newly added support area and the newly excavated surface area, and obtain the area matching degree that characterizes the timeliness of support follow-up. The time matching module is used to compare the exposure time of the newly excavated face area with the maximum allowable exposure time of the newly excavated face area, and calculate the time matching degree, which characterizes the tightness of the process connection, by means of a preset function. The preset function is a linear decay function or an exponential decay function. The evaluation result module is used to obtain the UAV inspection results of the current construction slope based on the speed matching degree, the area matching degree, and the time matching degree. The speed matching module is also used for: The actual average excavation speed is calculated based on the real-time excavation volume increment and the monitoring time interval. The speed ratio is obtained based on the actual average excavation speed and the planned excavation speed; The speed ratio is converted into a speed matching degree between 0 and 1 using a preset first mapping function.

9. An electronic device, characterized in that, include: At least one processor, at least one memory, and computer program instructions stored in the memory, which, when executed by the processor, implement the method as described in any one of claims 1-7.

Images