A real-time detection method and system for construction progress

Through technologies such as macro observation models and generative adversarial networks, the problems of cumbersome progress detection and accuracy deviation in the construction monitoring system are solved, and fast and accurate judgment and visualization of construction progress are achieved, reducing resource consumption.

CN118052447BActive Publication Date: 2024-12-06JIANGSU HAOHAN INFORMATION TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410176065.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-02-08
Publication Date
2024-12-06
Estimated Expiration
2044-02-08

AI Technical Summary

Technical Problem

The existing construction monitoring system has cumbersome and easy to miss when detecting construction progress, and cannot accurately detect construction progress. The traditional system consumes a lot of network bandwidth and computing resources, resulting in a deviation in monitoring accuracy.

Method used

The macro observation model and engineering guidance model are adopted to obtain project planning data, build project window sets and time models, combine the generative adversarial network to fill the window automatically, automatically capture and evaluate the construction progress, and set up hazard alarms for natural environment and construction equipment. Real-time detection and adjustment.

Benefits of technology

It realizes fast and accurate construction progress judgment and data call, improves the degree of visualization, reduces monitoring errors, and reduces the consumption of network and computing resources.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118052447B_ABST
    Figure CN118052447B_ABST
Patent Text Reader

Abstract

The present invention provides a method and system for real-time detection of construction progress. The method comprises: a macro observation module: obtaining engineering planning data and constructing a macro observation model; wherein the macro observation model is configured with a project window set, and each project window in the project window set is provided with an engineering project evaluation image; a window evaluation module: collecting engineering project construction data, dividing the engineering project construction data according to project windows, and inputting the data into each project window for window filling; a progress evaluation module: obtaining window filling results, and determining the construction progress based on the ratio of the filling area of ​​the project window to the total area of ​​the project window in the macro observation model.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of construction detection, and in particular to a real-time detection method and system for construction progress. Background Art

[0002] At present, infrastructure construction sites are numerous, wide and large in scale, and the progress of construction work must rely on supervisors to go to the site to evaluate the progress of construction. Although the infrastructure video surveillance system has been incorporated into the company's production safety management and control system, inspectors at all levels are required to conduct anti-violation inspections and construction progress inspections by watching the returned videos in real time or retrieving the stored historical videos later.

[0003] In the existing construction scenarios, we use edge control balls to connect terminals or the overall system platform. Although this technical solution can detect some slackness and realize the supervision of construction progress, it still requires a unified control platform and edge control to realize the calculation of project progress.

[0004] Usually, at construction sites, more accurate engineering monitoring is achieved by increasing the number of on-site surveillance cameras. However, because most traditional systems require cloud processing, the transmission of real-time video streams places increasingly high demands on network transmission bandwidth, greatly increasing network bandwidth requirements and increasing pressure on back-end servers. Therefore, this method will greatly increase the amount of computing power on the server, and therefore consumes a lot of computing resources.

[0005] In patent CN111126838B, a smart engineering management system is proposed, which monitors and analyzes the corresponding data through specific requirements for management in terms of comprehensiveness, safety, quality, progress, technology, and procurement. Through the information of personnel, machinery, materials, and environmental factors during construction, the comprehensive management system displays the monitoring status and data analysis of each system to the management personnel. The management personnel deploy the personnel, machinery, materials, and environment of the entire construction according to the observed data, and feed back the deployment information to each system. Each system adjusts its working situation according to the feedback deployment information, so as to enable the management personnel to grasp and control the entire construction situation.

[0006] However, it only proposed comprehensive management and control, but there were no specific calculation and monitoring requirements for the workers' workload and the use of materials on the construction site, and there were deviations in the accuracy of construction monitoring. Summary of the invention

[0007] The present invention provides a real-time detection method and system for construction progress, which are used to solve the problem that the construction progress cannot be accurately detected due to cumbersome monitoring and easy omission.

[0008] This application proposes a real-time construction progress detection method, including:

[0009] Obtain engineering planning data and build a macro observation model;

[0010] The macro observation model is configured with a project window set, and each project window in the project window set is provided with an engineering project evaluation image;

[0011] Collect engineering project construction data, divide the engineering project construction data according to project windows, and input it into each project window for window filling;

[0012] The window filling results are obtained, and the construction progress is determined based on the ratio of the filling area of ​​the project window to the total area of ​​the project window in the macro observation model.

[0013] Preferably, the engineering planning data includes the following acquisition steps:

[0014] Determine the site map of the construction site in advance, import the site map into the engineering simulation model, conduct engineering item analysis, and determine the engineering item data;

[0015] According to the project data, the project guidance model is constructed to generate multi-dimensional construction tasks;

[0016] The engineering guidance model is also used to predict and process additional items for multi-dimensional construction tasks, determine whether there are additional items for the project, and update the multi-dimensional construction tasks if there are additional items for the project;

[0017] Based on multi-dimensional construction tasks, a time model is constructed, and each task item in the multi-dimensional construction task is matched with the time model. The project item data is captured through the target capture algorithm of automatic modeling.

[0018] Divide the engineering item capture data according to the time model to determine the engineering planning data.

[0019] Preferably, the time model is also used for:

[0020] Pre-build an engineering planning model, roughly match the first point cloud data with the engineering planning model through a distance algorithm, and determine a first matching model;

[0021] Based on the ICP algorithm, the point cloud data and the first matching model are finely matched to obtain the engineering building model after the point cloud fusion;

[0022] Convert the engineering building model into an engineering display diagram through 3Dmax technology;

[0023] Generate a construction progress point cloud model through the project display diagram and project planning model;

[0024] According to the construction progress point cloud model, the engineering planning data is divided according to the time model.

[0025] Preferably, the macro observation model includes a project item window and a project item evaluation mechanism; wherein,

[0026] The project item window is used to import the project planning data into the corresponding project window according to the corresponding project;

[0027] The project item evaluation mechanism is embedded in the project item window and is used to compare and cover the project data imported into the project window and output the coverage area.

[0028] Preferably, the window filling includes:

[0029] Obtain construction project data;

[0030] The construction project data is input into the preset generative adversarial network for window division, and the window identification output by the generative adversarial network is obtained; wherein,

[0031] The generative adversarial network includes a generator and a dual-output discriminator;

[0032] Generative adversarial networks are trained as follows:

[0033] Get engineering construction samples, window type parameters and window import identifier loading parameters;

[0034] Inputting the engineering construction sample into the generator for pre-training to obtain a first recognition network output by the generator;

[0035] The engineering construction samples, window type parameters and window import identification loading parameters are input into the discriminator for training to obtain the discriminant branch of the discriminator;

[0036] According to the discriminant branch and the first identification network, the window corresponding to the construction data of the engineering project is determined, and the window identifier of the window data import identification mechanism is generated;

[0037] According to the window identification, the engineering project construction data is imported into different project windows for window filling.

[0038] Preferably, the setting of natural environment danger alarm and construction equipment danger alarm includes:

[0039] The natural environment danger alarm includes: rain and snow weather alarm, thunder and lightning weather alarm and other weather alarms; the construction equipment danger alarm includes: electrical equipment leakage alarm and mechanical equipment failure alarm;

[0040] When it is predicted that the construction site will experience rain or snow, the early warning system will issue a rain or snow weather alarm, and workers will take rain and snow protection measures on the construction site. Workers must complete the protection work and stop working immediately before the early warning ends;

[0041] When the construction site is predicted to experience thunderstorms, the early warning system will issue a thunderstorm alarm, and workers will cut off the power to electrical equipment on the construction site. Workers must complete protective work and stop operations immediately before the warning ends;

[0042] When the construction site is predicted to experience other weather conditions, the early warning system will issue other weather alarms, and workers will take protective measures on the construction site. Workers must complete the protective measures and stop working immediately before the early warning ends;

[0043] When there is a danger of leakage in electrical equipment on the construction site, the system will issue a leakage alarm, and the background monitoring personnel will immediately cut off the power switch of the specific leakage circuit, and dispatch maintenance personnel to detect and repair the accident circuit and obtain the detection and maintenance results;

[0044] When there is a risk of failure of mechanical equipment on the construction site, the system will issue a fault alarm, immediately stop the operation of the faulty mechanical equipment, and the inspection and maintenance personnel will inspect and repair the faulty equipment and obtain the inspection and maintenance results.

[0045] Preferably, the method further comprises:

[0046] Get the fill data of each item window;

[0047] Predetermine the upper and lower thresholds of the project progress corresponding to each project window;

[0048] According to the upper and lower thresholds, the project data is monitored for over-limit, and the degree of abnormality is determined based on the monitoring results.

[0049] Conduct an abnormality assessment on the construction data according to the abnormality degree of each window and determine the construction evaluation data;

[0050] Automatically audit each project window based on construction evaluation data.

[0051] Preferably, the method further comprises:

[0052] Obtain the original data required for various engineering projects;

[0053] Classify the raw data and set the data characteristics of each engineering project's raw data;

[0054] According to the data characteristics, determine the matching and identification mechanism for filling the data in each project window;

[0055] According to the matching recognition mechanism, the filled data of each project window is visually transformed to determine the visual data of different window projects.

[0056] Preferably, the determining of the construction progress further comprises:

[0057] Evaluate the construction progress into normal working progress range and abnormal progress range;

[0058] Based on the obtained accurate daily construction progress value, compare it with the preset construction progress range to obtain the comparison result;

[0059] According to the comparison result, when the construction progress is within the normal range, the level of the normal range of the construction progress is evaluated, and the level is evaluated and fed back;

[0060] When the construction progress falls within the abnormal range, the level of the abnormal range of the construction progress is evaluated, the level is evaluated and fed back, and a construction progress adjustment plan is formulated according to the level;

[0061] According to the construction progress adjustment plan, the construction progress will be adjusted to within the normal progress range.

[0062] A construction progress real-time detection system, the system comprising:

[0063] Macro observation module: obtain engineering planning data and build a macro observation model;

[0064] The macro observation model is configured with a project window set, and each project window in the project window set is provided with an engineering project evaluation image;

[0065] Window-based evaluation module: collects engineering project construction data, divides the engineering project construction data according to project windows, and inputs it into each project window for window filling;

[0066] Progress evaluation module: obtains the window filling results and determines the construction progress based on the ratio of the filling area of ​​the project window to the total area of ​​the project window in the macro observation model.

[0067] The beneficial effects of the present invention are:

[0068] 1. Determine whether the project progress is fast enough;

[0069] 2. When determining the progress of each small project, you can quickly call the data and quickly locate the data of each small project;

[0070] 3. The degree of visualization is relatively high.

[0071] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0072] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0074] Figure 1 This is a flow chart of a method for real-time detection of construction progress in an embodiment of the present invention;

[0075] Figure 2 This is a system composition diagram of a construction progress real-time detection system in an embodiment of the present invention;

[0076] Figure 3 A point cloud diagram of the entire construction site in an embodiment of the present invention;

[0077] Figure 4 A point cloud image of a building in a construction site in an embodiment of the present invention;

[0078] Figure 5 This is a 3Dmax construction progress determination diagram in an embodiment of the present invention. DETAILED DESCRIPTION

[0079] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0080] As attached Figure 1 As shown, an embodiment of the present invention provides a method for real-time detection of construction progress, comprising:

[0081] Obtain engineering planning data and build a macro observation model;

[0082] The macro observation model is configured with a project window set, and each project window in the project window set is provided with an engineering project evaluation image;

[0083] Collect engineering project construction data, divide the engineering project construction data according to project windows, and input it into each project window for window filling;

[0084] The window filling results are obtained, and the construction progress is determined based on the ratio of the filling area of ​​the project window to the total area of ​​the project window in the macro observation model.

[0085] The principle of the above technical solution is:

[0086] As attached Figure 1As shown, the engineering planning data of this application is related to the planning data of the engineering project, such as design drawings, engineering budget, etc.; the macro observation model is a macro model of the overall construction site. There are many data detection windows in the macro detection model. Each data detection window corresponds to the project data of any project of the chief engineer, or it can be a project image; the main component of the macro observation model is the "project window set", and each "project window" contains one or more specific engineering project information, such as the project name, location, expected construction period, etc. In addition, the "project window set" also has an important feature, that is, each "project window" has a corresponding "engineering project evaluation image". This "engineering project evaluation image" is generated by us based on the engineering planning data, which can intuitively reflect the overall progress of the engineering project, including the completed workload, the remaining workload, the engineering quality and other information. Through each small project window, and then through the collected data, the completion of each small project is determined by filling and covering; by comparing the area of ​​each small project window with the total area of ​​the total project window, the construction progress can be judged. In actual implementation, data is collected on the actual situation of the project construction, including the actual progress of the project, the actual amount of work completed, the actual human and material resources invested, etc. These real-time data are divided according to the "project window" and input into each "project window" for window filling. The "window filling" here is not a real image display, but a virtual value calculated based on these real-time data, which represents the actual progress of the current project. Finally, by analyzing the filling area of ​​the "project window" and "project window collection" in the macro observation model and the total area of ​​the entire model, a ratio is calculated, which is the construction progress. In this way, an accurate and real-time construction progress can be obtained, which is very helpful for the management and adjustment of the construction site.

[0087] The beneficial effects of the above technical solution are:

[0088] 1. Determine whether the project progress is fast enough;

[0089] 2. When determining the progress of each small project, you can quickly call the data and quickly locate the data of each small project;

[0090] 3. The degree of visualization is relatively high.

[0091] As an embodiment of the present application, the engineering planning data includes the following acquisition steps:

[0092] Determine the site map of the construction site in advance, import the site map into the engineering simulation model, conduct engineering item analysis, and determine the engineering item data;

[0093] According to the project data, the project guidance model is constructed to generate multi-dimensional construction tasks;

[0094] The engineering guidance model is also used to predict and process additional items for multi-dimensional construction tasks, determine whether there are additional items for the project, and update the multi-dimensional construction tasks if there are additional items for the project;

[0095] Based on multi-dimensional construction tasks, a time model is constructed, and each task item in the multi-dimensional construction task is matched with the time model. The project item data is captured through the target capture algorithm of automatic modeling.

[0096] Divide the engineering item capture data according to the time model to determine the engineering planning data.

[0097] The principle of the above technical solution is:

[0098] In actual implementation, this application predetermines the on-site map of the construction site, and the map can be obtained by field survey. Then, the on-site map is imported into the engineering simulation model for engineering item analysis, and the data of the engineering items, such as engineering quantity, construction period, budget, etc., can be determined. Then, using these determined engineering item data, our engineering guidance model is constructed. The engineering guidance model can be used not only to generate multi-dimensional construction tasks, but also to predict and process the multi-dimensional construction tasks. By judging whether there are engineering additions, the multi-dimensional construction tasks can be updated if necessary. After the engineering guidance model is constructed, the time model is constructed based on this model. The time model can determine the specific start and end time of each task, so as to better manage the progress of the project. Finally, the time model and the multi-dimensional construction tasks are matched, and the target capture algorithm of automatic modeling is used, so that the data of the engineering items can be captured more accurately. These data will be divided according to the time model to determine the final engineering planning data.

[0099] The beneficial effects of the above technical solution are:

[0100] In terms of engineering planning data acquisition, this application uses simulation to perform overall engineering modeling, but in addition to simulation, it implements multi-dimensional division, after which additional item predictions can be made and additional engineering items can be determined.

[0101] As an embodiment of the present application, the time model is also used for:

[0102] Pre-build an engineering planning model, roughly match the first point cloud data with the engineering planning model through a distance algorithm, and determine a first matching model;

[0103] Based on the ICP algorithm, the point cloud data and the first matching model are finely matched to obtain the engineering building model after the point cloud fusion;

[0104] Convert the engineering building model into an engineering display diagram through 3Dmax technology;

[0105] Generate a construction progress point cloud model through the project display diagram and project planning model;

[0106] According to the construction progress point cloud model, the engineering planning data is divided according to the time model.

[0107] The principle of the above technical solution is:

[0108] This application can pre-build an engineering planning model, specifically use a distance algorithm to roughly match the first point cloud data (i.e. the actual situation at the construction site) and the engineering planning model to determine a preliminary matching model. Then, based on the ICP (Iterative Closest Point) algorithm, the point cloud data (i.e. the actual situation at the construction site) and the first matching model are finely matched. This process can obtain an engineering building model after point cloud fusion, which will more accurately reflect the actual situation at the construction site. The engineering building model is converted into an engineering display diagram through 3Dmax technology, and the changes in the progress of the project can be understood in real time by observing this engineering display diagram. A construction progress point cloud model is generated through the engineering display diagram and the engineering planning model. This model contains real-time progress information of the construction site and can provide more detailed engineering progress information. According to the construction progress point cloud model, the engineering planning data is divided according to the time model. In this way, a set of engineering planning data that can change according to time is obtained, and this data can be used to monitor the progress of the project in real time.

[0109] The beneficial effects of the above technical solution are:

[0110] This application makes judgments through the fusion of point cloud data and engineering planning data. When judging the construction progress, it can be based on the point cloud model of the construction progress. The point cloud model and the judgment window are combined to achieve higher efficiency.

[0111] As an embodiment of the present application, the macro observation model includes an engineering item window and an engineering item evaluation mechanism; wherein,

[0112] The project item window is used to import the project planning data into the corresponding project window according to the corresponding project;

[0113] The project item evaluation mechanism is embedded in the project item window and is used to compare and cover the project data imported into the project window and output the coverage area.

[0114] The principle of the above technical solution is:

[0115] like Figures 3 to 5As shown, the engineering item window of the present application is responsible for importing and displaying the corresponding engineering planning data, and each engineering item window corresponds to a specific engineering project. The engineering item evaluation mechanism is nested in the engineering item window, responsible for comparing and evaluating the imported engineering data, and outputting the coverage area. In specific implementation, the engineering item evaluation mechanism may adopt technologies such as pixel-level comparison and deep learning to accurately measure and calculate the coverage area. In the process of calculating the coverage area, technologies such as coordinate system conversion and area overlap detection are used.

[0116] The beneficial effects of the above technical solution are:

[0117] The present application can judge the construction progress by the coverage area and realize instant completion judgment without the need for data processing, so there will be no errors in data recognition.

[0118] As an embodiment of the present application, the window filling includes:

[0119] Obtain construction project data;

[0120] The construction project data is input into the preset generative adversarial network for window division, and the window identification output by the generative adversarial network is obtained; wherein,

[0121] The generative adversarial network includes a generator and a dual-output discriminator;

[0122] Generative adversarial networks are trained as follows:

[0123] Get engineering construction samples, window type parameters and window import identifier loading parameters;

[0124] Inputting the engineering construction sample into the generator for pre-training to obtain a first recognition network output by the generator;

[0125] The engineering construction samples, window type parameters and window import identification loading parameters are input into the discriminator for training to obtain the discriminant branch of the discriminator;

[0126] According to the discriminant branch and the first identification network, the window corresponding to the construction data of the engineering project is determined, and the window identifier of the window data import identification mechanism is generated;

[0127] According to the window identification, the engineering project construction data is imported into different project windows for window filling.

[0128] The principle of the above technical solution is:

[0129] This application uses a pre-set generative adversarial network to perform window division, thereby realizing real-time monitoring of engineering project construction data. In actual implementation, for window filling, it is divided into two steps. The first step is to obtain engineering project construction data, and the second step is to input these data into a preset generative adversarial network for window division. In the generative adversarial network, it has a unique structural design. The network not only includes a generator, but also is equipped with a dual-output discriminator, so that the entire model can more accurately identify various types of engineering project construction data. During the training process of the generative adversarial network, a series of engineering construction samples, window type parameters, and window import identification loading parameters are obtained by preprocessing. Then this information is input into the generator and the discriminator for pre-training. In this process, the generator will learn and adapt to the input engineering construction samples, thereby generating a first recognition network. The discriminator will classify and identify the input information, and then generate a discriminant branch. After completing the pre-training, the window corresponding to the engineering project construction data will be determined according to the discriminant branch and the first recognition network. Finally, the engineering project construction data is imported into different project windows for filling according to the window identification. This process is very intelligent because it uses the knowledge learned in the generative adversarial network to automatically fill the data in the correct location.

[0130] The beneficial effects of the above technical solution are:

[0131] In the process of window determination, the generative adversarial network can be used to automatically determine the data and automatically import the corresponding progress determination window.

[0132] As an embodiment of the present application, the setting of natural environment danger alarm and construction equipment danger alarm includes:

[0133] The natural environment danger alarm includes: rain and snow weather alarm, thunder and lightning weather alarm and other weather alarms; the construction equipment danger alarm includes: electrical equipment leakage alarm and mechanical equipment failure alarm;

[0134] When it is predicted that the construction site will experience rain or snow, the early warning system will issue a rain or snow weather alarm, and workers will take rain and snow protection measures on the construction site. Workers must complete the protection work and stop working immediately before the early warning ends;

[0135] When the construction site is predicted to experience thunderstorms, the early warning system will issue a thunderstorm alarm, and workers will cut off the power to electrical equipment on the construction site. Workers must complete protective work and stop operations immediately before the warning ends;

[0136] When the construction site is predicted to experience other weather conditions, the early warning system will issue other weather alarms, and workers will take protective measures on the construction site. Workers must complete the protective measures and stop working immediately before the early warning ends;

[0137] When there is a danger of leakage in electrical equipment on the construction site, the system will issue a leakage alarm, and the background monitoring personnel will immediately cut off the power switch of the specific leakage circuit, and dispatch maintenance personnel to detect and repair the accident circuit and obtain the detection and maintenance results;

[0138] When there is a risk of failure of mechanical equipment on the construction site, the system will issue a fault alarm, immediately stop the operation of the faulty mechanical equipment, and the inspection and maintenance personnel will inspect and repair the faulty equipment and obtain the inspection and maintenance results.

[0139] The principle of the above technical solution is:

[0140] During the specific implementation process, this application will also monitor the natural environment and construction equipment at the construction site. The natural environment hazard alarm will issue warnings for possible severe weather conditions such as rain, snow, thunder and lightning, reminding workers to take corresponding protective measures under these conditions to ensure personal safety and construction progress.

[0141] For construction equipment danger alarm, it will monitor possible equipment failures. Once an abnormality is found in the equipment, it will immediately sound an alarm, cut off the power supply or suspend operations to prevent the equipment failure from expanding or causing serious consequences. At the same time, the background monitoring personnel will promptly send maintenance personnel to conduct on-site inspections and repairs according to the alarm situation to restore the normal operation of the equipment as soon as possible and ensure that the construction progress is not affected.

[0142] As an embodiment of the present application, the method further includes:

[0143] Get the fill data of each item window;

[0144] Predetermine the upper and lower thresholds of the project progress corresponding to each project window;

[0145] According to the upper and lower thresholds, the project data is monitored for over-limit, and the degree of abnormality is determined based on the monitoring results.

[0146] Conduct an abnormality assessment on the construction data according to the abnormality degree of each window and determine the construction evaluation data;

[0147] Automatically audit each project window based on construction evaluation data.

[0148] The principle of the above technical solution is:

[0149] This application obtains the fill data of each project window, including the actual upper and lower thresholds of the project progress corresponding to each project window, which are predetermined, and monitors the data of each project window for over-limit. When the monitored data exceeds the set threshold, it indicates that there is an abnormality in the project progress. Information such as completed workload, expected workload, actual human and material resources invested, etc. Determine the degree of abnormality based on the results of over-limit monitoring. If the degree of abnormality is low, only some simple adjustments may be required, such as increasing the investment in human and material resources; if the degree of abnormality is high, more proactive measures may need to be taken, such as rescheduling work plans. For construction evaluation data, each project window can be automatically audited to ensure that the project progress meets expectations and to promptly identify and correct any potential problems.

[0150] As an embodiment of the present application, the method further includes:

[0151] Obtain the original data required for various engineering projects;

[0152] Classify the raw data and set the data characteristics of each engineering project's raw data;

[0153] According to the data characteristics, determine the matching and identification mechanism for filling the data in each project window;

[0154] According to the matching recognition mechanism, the filled data of each project window is visually transformed to determine the visual data of different window projects.

[0155] The principle of the above technical solution is:

[0156] This application obtains the original data required for various engineering projects, such as engineering design drawings, contract documents, on-site observation records, etc. The original data is classified and the data characteristics of the original data of each engineering project are set. In the subsequent window filling data processing and matching process, the data can be identified and matched more accurately. According to the data characteristics, the matching recognition mechanism for filling the window data of each project is determined. For example, matching can be performed according to the type of data, time range or keywords. According to the matching recognition mechanism, the filling data of each project window is visually converted to determine the visual data of different window projects. This makes the data easier to understand and compare visually.

[0157] The beneficial effects of the above technical solution are:

[0158] For different project windows, this application can directly visualize different data according to the database during visualization conversion.

[0159] As an embodiment of the present application, determining the construction progress further includes:

[0160] Evaluate the construction progress into normal working progress range and abnormal progress range;

[0161] Based on the obtained accurate daily construction progress value, compare it with the preset construction progress range to obtain the comparison result;

[0162] According to the comparison result, when the construction progress is within the normal range, the level of the normal range of the construction progress is evaluated, and the level is evaluated and fed back;

[0163] When the construction progress falls within the abnormal range, the level of the abnormal range of the construction progress is evaluated, the level is evaluated and fed back, and a construction progress adjustment plan is formulated according to the level;

[0164] According to the construction progress adjustment plan, the construction progress will be adjusted to within the normal progress range.

[0165] The principle of the above technical solution is:

[0166] This application compares the obtained daily accurate construction progress value with the preset construction progress range to obtain a comparison result. The preset construction progress range refers to the expected construction progress range of the engineering project specified in the engineering plan. According to the comparison results, when the construction progress is within the normal range, the level of the normal range of the construction progress is evaluated, and the level is evaluated and fed back. The evaluation level here can be ABCDEF, etc., representing different progress conditions respectively. When the construction progress is within the abnormal range, the level of the abnormal range of the construction progress is evaluated, and the level is evaluated and fed back. At the same time, a corresponding construction progress adjustment plan can also be formulated according to the level. According to the formulated construction progress adjustment plan, the construction progress is adjusted to within the normal progress range. This can be achieved through manual intervention or automation.

[0167] The beneficial effects of the above technical solution are:

[0168] This application can compare the construction progress, determine whether the construction progress is abnormal, and adjust the construction progress; it can also implement direct adjustment.

[0169] A construction progress real-time detection system, the system comprising:

[0170] Macro observation module: obtain engineering planning data and build a macro observation model;

[0171] The macro observation model is configured with a project window set, and each project window in the project window set is provided with an engineering project evaluation image;

[0172] Window-based evaluation module: collects engineering project construction data, divides the engineering project construction data according to project windows, and inputs it into each project window for window filling;

[0173] Progress evaluation module: obtains the window filling results and determines the construction progress based on the ratio of the filling area of ​​the project window to the total area of ​​the project window in the macro observation model.

[0174] like Figure 2 As shown, the engineering planning data of this application is related to the planning data of the engineering project, such as design drawings, engineering budget, etc.; the macro observation model is a macro model of the overall construction site. There are many data detection windows in the macro detection model. Each data detection window corresponds to the project data of any project of the chief engineer, or it can be a project image; the main component of the macro observation model is the "project window set", and each "project window" contains one or more specific engineering project information, such as the project name, location, expected construction period, etc. In addition, the "project window set" also has an important feature, that is, each "project window" has a corresponding "engineering project evaluation image". This "engineering project evaluation image" is generated by us based on the engineering planning data, which can intuitively reflect the overall progress of the engineering project, including the completed workload, the remaining workload, the engineering quality and other information. Through each small project window, and then through the collected data, the completion of each small project is determined by filling and covering; by comparing the area of ​​each small project window with the total area of ​​the total project window, the construction progress can be judged.

[0175] In actual implementation, data is collected on the actual situation of the project construction, including the actual progress of the project, the actual amount of work completed, the actual human and material resources invested, etc. These real-time data are divided according to the "project window" and input into each "project window" for window filling. The "window filling" here is not a real image display, but a virtual value calculated based on these real-time data, which represents the actual progress of the current project. Finally, by analyzing the filling area of ​​the "project window" and "project window collection" in the macro observation model and the total area of ​​the entire model, a ratio is calculated, which is the construction progress. In this way, an accurate and real-time construction progress can be obtained, which is very helpful for the management and adjustment of the construction site.

[0176] The beneficial effects of the above technical solution are:

[0177] 1. Determine whether the project progress is fast enough;

[0178] 2. When determining the progress of each small project, you can quickly call the data and quickly locate the data of each small project;

[0179] 3. The degree of visualization is relatively high.

[0180] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A real-time detection method for construction progress, It is characterized in that include: Obtain engineering planning data and build a macro observation model; The macro observation model is configured with a project window set, and each project window in the project window set is provided with an engineering project evaluation image; Collect engineering project construction data, divide the engineering project construction data according to project windows, and input it into each project window for window filling; Obtain the window filling results and determine the construction progress based on the ratio of the filling area of ​​the project window to the total area of ​​the project window in the macro observation model; The macro observation model includes a project window and a project evaluation mechanism; wherein, The project item window is used to import the project planning data into the corresponding project window according to the corresponding project; The project item evaluation mechanism is embedded in the project item window, which is used to compare and cover the project data imported into the project window and output the coverage area; The window filling includes: Obtain construction project data; The construction project data is input into the preset generative adversarial network for window division, and the window identification output by the generative adversarial network is obtained; wherein, The generative adversarial network includes a generator and a dual-output discriminator; Generative adversarial networks are trained as follows: Get engineering construction samples, window type parameters and window import identifier loading parameters; Inputting the engineering construction sample into the generator for pre-training to obtain a first recognition network output by the generator; The engineering construction samples, window type parameters and window import identification loading parameters are input into the discriminator for training to obtain the discriminant branch of the discriminator; Determine the window corresponding to the construction data of the engineering project according to the discriminant branch and the first identification network, and generate a window identifier for importing the window data into the identification mechanism; According to the window identification, the construction data of the engineering project is imported into different project windows for window filling; The method further comprises: Get the fill data of each item window; Predetermine the upper and lower thresholds of the project progress corresponding to each project window; According to the upper and lower thresholds, the project data is monitored for over-limits, and the degree of abnormality is determined based on the over-limit monitoring results; Conduct an abnormality assessment on the construction data according to the abnormality degree of each window and determine the construction evaluation data; Automatically audit each project window based on construction evaluation data.

2. A method for real-time detection of construction progress as claimed in claim 1, It is characterized in that The engineering planning data includes the following acquisition steps: Determine the site map of the construction site in advance, import the site map into the engineering simulation model, conduct engineering item analysis, and determine the engineering item data; According to the project data, the project guidance model is constructed to generate multi-dimensional construction tasks; The engineering guidance model is also used to predict and process additional items for multi-dimensional construction tasks, determine whether there are additional items for the project, and update the multi-dimensional construction tasks if there are additional items for the project; Based on multi-dimensional construction tasks, a time model is constructed, and each task item in the multi-dimensional construction task is matched with the time model. The project item data is captured through the target capture algorithm of automatic modeling. Divide the engineering item capture data according to the time model to determine the engineering planning data.

3. A method for real-time detection of construction progress as claimed in claim 2, It is characterized in that The time model is also used to: Pre-build an engineering planning model, roughly match the first point cloud data with the engineering planning model through a distance algorithm, and determine a first matching model; Based on the ICP algorithm, the point cloud data and the first matching model are finely matched to obtain the engineering building model after the point cloud fusion; Convert the engineering building model into an engineering display diagram through 3Dmax technology; Generate a construction progress point cloud model through the project display diagram and project planning model; According to the construction progress point cloud model, the engineering planning data is divided according to the time model.

4. A method for real-time detection of construction progress as claimed in claim 1, It is characterized in that The method further includes setting a natural environment danger alarm and a construction equipment danger alarm: The natural environment danger alarm includes: rain and snow weather alarm, thunder and lightning weather alarm and other weather alarms; the construction equipment danger alarm includes: electrical equipment leakage alarm and mechanical equipment failure alarm; When it is predicted that the construction site will experience rain or snow, the early warning system will issue a rain or snow weather alarm, and workers will take rain and snow protection measures on the construction site. Workers must complete the protection work and stop working immediately before the early warning ends; When the construction site is predicted to experience thunderstorms, the early warning system will issue a thunderstorm alarm, and workers will cut off the power to electrical equipment on the construction site. Workers must complete protective work and stop operations immediately before the warning ends; When the construction site is predicted to experience other weather conditions, the early warning system will issue other weather alarms, and workers will take protective measures on the construction site. Workers must complete the protective measures and stop working immediately before the early warning ends; When there is a danger of leakage in electrical equipment on the construction site, the system will issue a leakage alarm, and the background monitoring personnel will immediately cut off the power switch of the specific leakage circuit, and dispatch maintenance personnel to detect and repair the accident circuit and obtain the detection and maintenance results; When there is a risk of failure of mechanical equipment on the construction site, the system will issue a fault alarm, immediately stop the operation of the faulty mechanical equipment, and the inspection and maintenance personnel will inspect and repair the faulty equipment and obtain the inspection and maintenance results.

5. A method for real-time detection of construction progress as claimed in claim 1, It is characterized in that The method further comprises: Obtain the original data required for various engineering projects; Classify the raw data and set the data characteristics of each engineering project's raw data; According to the data characteristics, determine the matching and identification mechanism for filling the data in each project window; According to the matching recognition mechanism, the filled data of each project window is visually transformed to determine the visual data of different window projects.

6. A method for real-time detection of construction progress as claimed in claim 1, It is characterized in that Determining the construction progress also includes: Evaluate the construction progress into normal working progress range and abnormal progress range; Based on the obtained accurate daily construction progress value, compare it with the preset construction progress range to obtain the comparison result; According to the comparison result, when the construction progress is within the normal range, the level of the normal range of the construction progress is evaluated, and the level is evaluated and fed back; When the construction progress falls within the abnormal range, the level of the abnormal range of the construction progress is evaluated, the level is evaluated and fed back, and a construction progress adjustment plan is formulated according to the level; According to the construction progress adjustment plan, the construction progress will be adjusted to within the normal progress range.

7. A real-time construction progress detection system, It is characterized in that The system comprises: Macro observation module: obtain engineering planning data and build a macro observation model; The macro observation model is configured with a project window set, and each project window in the project window set is provided with an engineering project evaluation image; Window-based evaluation module: collects engineering project construction data, divides the engineering project construction data according to project windows, and inputs it into each project window for window filling; Progress evaluation module: obtains the window filling results and determines the construction progress based on the ratio of the filling area of ​​the project window to the total area of ​​the project window in the macro observation model; The macro observation model includes a project window and a project evaluation mechanism; wherein, The project item window is used to import the project planning data into the corresponding project window according to the corresponding project; The project item evaluation mechanism is embedded in the project item window, which is used to compare and cover the project data imported into the project window and output the coverage area; The window filling includes: Obtain construction project data; The construction project data is input into the preset generative adversarial network for window division, and the window identification output by the generative adversarial network is obtained; wherein, The generative adversarial network includes a generator and a dual-output discriminator; Generative adversarial networks are trained as follows: Get engineering construction samples, window type parameters and window import identifier loading parameters; Inputting the engineering construction sample into the generator for pre-training to obtain a first recognition network output by the generator; The engineering construction samples, window type parameters and window import identification loading parameters are input into the discriminator for training to obtain the discriminant branch of the discriminator; Determine the window corresponding to the construction data of the engineering project according to the discriminant branch and the first identification network, and generate a window identifier for importing the window data into the identification mechanism; According to the window identification, the construction data of the engineering project is imported into different project windows for window filling; The system further comprises: Get the fill data of each item window; Predetermine the upper and lower thresholds of the project progress corresponding to each project window; According to the upper and lower thresholds, the project data is monitored for over-limits, and the degree of abnormality is determined based on the over-limit monitoring results; Conduct an abnormality assessment on the construction data according to the abnormality degree of each window and determine the construction evaluation data; Automatically audit each project window based on construction evaluation data.