CN116050772A - Engineering supervision method and system based on BIM - Google Patents
Engineering supervision method and system based on BIM Download PDFInfo
- Publication number
- CN116050772A CN116050772A CN202310048414.0A CN202310048414A CN116050772A CN 116050772 A CN116050772 A CN 116050772A CN 202310048414 A CN202310048414 A CN 202310048414A CN 116050772 A CN116050772 A CN 116050772A
- Authority
- CN
- China
- Prior art keywords
- engineering
- data
- construction
- model
- bim
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06314—Calendaring for a resource
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/16—Image preprocessing
- G06V30/164—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/42—Document-oriented image-based pattern recognition based on the type of document
- G06V30/422—Technical drawings; Geographical maps
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The application relates to the technical field of engineering supervision, and particularly discloses a BIM-based engineering supervision method and system, which comprise the following steps: building a standard BIM model according to engineering design information, wherein the engineering design information comprises engineering design schemes, engineering design drawings and construction progress plans of a plurality of construction nodes; building an engineering BIM module according to site construction information, wherein the engineering construction information comprises site construction data information of a current construction node; determining model difference data based on the standard BIM model and the engineering BIM model; and outputting a supervision analysis result based on the model difference data. The engineering progress and the quality can be visually reflected through BIM model comparison, management staff can control the engineering quality and the engineering progress, and engineering management efficiency is improved.
Description
Technical Field
The application relates to the technical field of engineering supervision, in particular to a BIM-based engineering supervision method and system.
Background
In recent years, with the comprehensive promotion and wide application of the Internet plus and the building informatization, a building information model (Building Information Modeling, BIM for short) serving as an important tool and a product for promoting the building informatization becomes an indispensable tool in the Internet plus building industry, and the implementation mode of the building information model also determines that the Internet plus social and economic benefits are realized in the building industry in China.
The construction project supervision is entrusted by a constructor, and according to laws and regulations, project construction standards, investigation design files and contracts, the construction project quality, the construction cost and the progress are controlled in the construction stage, the contracts and the information are managed, the relation of the project construction related parties is coordinated, and the service activities of legal responsibility of construction project safety generation management are fulfilled.
Along with the popularization of BIM technology, the method is gradually applied to engineering supervision work, but the existing engineering supervision system or method based on the BIM technology has single function and cannot meet the requirements of enterprises on digital engineering supervision.
Disclosure of Invention
Aiming at the problems that the existing engineering supervision method or system based on BIM technology is single in application and low in application degree of engineering supervision digitization, the application provides the engineering supervision method and system based on BIM.
According to one aspect of the present application, there is provided a BIM-based engineering supervision method, including:
building a standard BIM model according to engineering design information, wherein the engineering design information comprises engineering design schemes, engineering design drawings and construction progress plans of a plurality of construction nodes;
constructing an engineering BIM module according to site construction information, wherein the engineering construction information comprises site construction data information of a current construction node;
determining model difference data based on the standard BIM model and the engineering BIM model;
and outputting a supervision analysis result based on the model difference data.
Preferably, building a standard BIM model according to engineering design information includes:
engineering design scheme data are acquired, wherein the engineering design scheme data comprise engineering quantity data and construction scheme data of engineering, project construction operation flow and supply plans of material instruments;
engineering design drawing data are obtained, wherein the engineering design drawing data comprise engineering indoor and outdoor elevation drawing data, indoor and outdoor 3D effect drawing data, engineering plane drawing data and manufacturing standard information;
acquiring construction progress plan data, wherein the construction progress plan data comprises a construction progress plan of a construction project and a progress plan of a construction preparation stage;
and constructing a standard BIM model based on the engineering design scheme data, the engineering design drawing data and the construction progress plan data of the plurality of construction nodes.
Preferably, building the engineering BIM model according to the site construction information comprises:
acquiring engineering supervision operation information;
acquiring site construction data based on the data acquisition unit;
acquiring engineering site image data based on an image acquisition unit;
denoising the image data based on the image processing unit;
and building an engineering BIM model based on the engineering supervision operation information of the plurality of construction nodes and the engineering site image data.
Preferably, the denoising processing of the image data based on the image processing unit includes:
constructing a pair of training data set and verification data set according to the obtained image data and sampling in Gaussian distribution with known variance to obtain additive noise, and preprocessing the training data set;
taking the convolutional neural network as a Boosting unit, and building a depth lifting frame model based on an SOS algorithm;
training the depth lifting frame model by utilizing the preprocessed training data set, and adjusting corresponding model parameters;
adjusting the structural super-parameters and the optimization super-parameters of the trained depth lifting frame model by using the verification data set; and verifying the depth lifting frame model by using the verification data set, and selecting the model parameter with the minimum recovery loss, thereby determining a final depth lifting frame model, and finally obtaining the field image data after the enhancement processing based on the depth lifting frame model.
Preferably, constructing a pair of training data set and verification data set from the obtained image data and sampling additive noise in a gaussian distribution of known variance, and preprocessing the training data set includes:
assuming that the acquired image data is a, the image data is distributed in a sigma gaussian distribution N (0, sigma 2 ) The additive noise V with the same resolution is obtained through the middle sampling;
adding noise V into a natural image A to obtain image data Y=A+V with noise, wherein Y in each pair of image data is used as the input of a depth lifting frame model, and A is used as a training target;
several sets of paired image data (Y, a) are collected, separated by a proportion, to form a training dataset D and a validation dataset V for redemption.
Preferably, determining model difference data based on the standard BIM model and the engineering BIM model includes:
identifying difference data of a standard BIM model and an engineering BIM model based on a comparison unit, wherein the difference data comprises structure elevation difference data, space coordinate difference data, material difference data and progress difference data;
and outputting model difference data.
Preferably, determining model difference data based on the standard BIM model and the engineering BIM model includes:
comparing the difference data with a preset difference threshold value, and judging the difference degree;
and when the difference data exceeds a preset difference threshold, sending early warning information to terminal equipment of the supervision personnel.
Preferably, outputting the supervision analysis result based on the model difference data includes:
and establishing a deep reinforcement learning model, wherein the engineering design scheme comprises construction quality standard data, the construction data information comprises actual construction quality data, and the deep reinforcement learning model is used for determining an engineering supervision result of the construction node based on the construction quality standard data, the actual construction quality data and the model difference data.
Preferably, the deep reinforcement learning model uses model difference data, construction quality standard data and actual construction quality data as environmental state information, uses a supervision analysis result as a decision target, and is further used for inputting the environmental state information as the deep learning model, uses the decision target as the output of the deep reinforcement learning model, and the action space of the deep reinforcement learning model contains engineering quality anomaly.
According to another aspect of the present application, there is also provided a BIM-based engineering supervision system, including:
the standard BIM module is used for building a standard BIM model according to engineering design information, wherein the engineering design information comprises engineering design schemes, engineering design drawings and construction progress plans of a plurality of construction nodes;
the engineering BIM module is built according to site construction information, wherein the engineering construction information comprises site construction data information of the current construction node;
the comparison module is used for determining model difference data based on a standard BIM model and an engineering BIM model;
and the processing module is used for outputting a supervision analysis result based on the model difference data.
In summary, the present application includes the following beneficial technical effects:
building a standard BIM model according to engineering design information, wherein the engineering design information comprises engineering design schemes, engineering design drawings and construction progress plans of a plurality of construction nodes; constructing an engineering BIM module according to site construction information, wherein the engineering construction information comprises site construction data information of a current construction node; determining model difference data based on the standard BIM model and the engineering BIM model; and outputting a supervision analysis result based on the model difference data. The engineering progress and the quality can be visually reflected through BIM model comparison, management staff can control the engineering quality and the engineering progress, and engineering management efficiency is improved.
Drawings
Fig. 1 is a schematic flow chart of a method for engineering supervision based on BIM in the present application.
FIG. 2 is a schematic flow chart of building a standard BIM model according to engineering design information in the application.
Fig. 3 is a schematic flow chart of building engineering BIM model according to site construction information in the present application.
Fig. 4 is a schematic flow chart of denoising processing for image data based on an image processing unit in the present application.
Fig. 5 is a schematic structural diagram of the engineering supervision system based on BIM in the present application.
Detailed Description
The objects, technical solutions and advantages of the present application will become more apparent hereinafter, and the present application will be further described in detail by means of the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
Fig. 1 is a schematic flow chart of a method for engineering supervision based on BIM in the present application.
As shown in fig. 1, the present application provides a building information management method based on BIM, including:
s102, building a standard BIM model according to engineering design information, wherein the engineering design information comprises engineering design schemes, engineering design drawings and construction progress plans of a plurality of construction nodes.
One engineering project usually includes a plurality of construction nodes, and the construction nodes may be a certain time node in the engineering, or may be structural sub-engineering of the engineering project, for example: foundation engineering, basement engineering, hydroelectric engineering, fire engineering, greening engineering and the like.
In one embodiment, a project supervisor can divide the project construction nodes according to the WBS model, determine a work decomposition structure according to the WBS model, define the project construction process flow, and construct a standard BIM model of the current construction nodes according to the actual work progress. Wherein, a construction node corresponds to a standard BIM model.
FIG. 2 is a schematic flow chart of building a standard BIM model according to engineering design information in the application.
As shown in fig. 2, building a standard BIM model according to engineering design information includes:
s202, engineering design scheme data are acquired, wherein the engineering design scheme data comprise engineering quantity data and construction scheme data of an engineering, project construction operation flow and a supply plan of material instruments.
S204, engineering design drawing data are obtained, wherein the engineering design drawing data comprise engineering indoor and outdoor elevation drawing data, indoor and outdoor 3D effect drawing data, engineering plan drawing data and manufacturing standard information.
S206, acquiring construction progress plan data, wherein the construction progress plan data comprises a construction progress plan of a construction project and a progress plan of a construction preparation stage;
s208, building a standard BIM model based on engineering design scheme data, engineering design drawing data and construction progress plan data of a plurality of construction nodes.
The BIM model based on the engineering design information is used for building a standard, so that the quality standard, the construction progress plan and the construction effect data of the engineering can be modeled in a three-dimensional mode, and personnel can conveniently realize digital management and control of the quality and the progress of the engineering based on the BIM model.
S104, building an engineering BIM module according to site construction information, wherein the engineering construction information comprises site construction data information of the current construction node.
Fig. 3 is a schematic flow chart of building engineering BIM model according to site construction information in the present application.
As shown in fig. 3, building an engineering BIM model according to site operation information includes:
s302, acquiring engineering supervision operation information.
The project supervision operation information comprises a project supervision operation table, and a supervision person inputs the project supervision operation table according to actual project supervision operation content and supervision information acquired in an operation process, wherein the project supervision operation table comprises: engineering progress information, inspection data information, site inspection information, and the like.
In one embodiment, the proctoring and personnel detect the local structure of the project to obtain detection data of the local structure, for example: the method comprises the steps of acquiring an image of an engineering structure through an acquisition device, inputting the information by establishing engineering supervision operation, establishing a three-dimensional model based on the information such as the detection data, and causing the three-dimensional model to be in a BIM model.
S304, acquiring site construction data based on the data acquisition unit.
In one embodiment, the on-site constructor performs on-site construction data entry according to the actual construction operation content and the construction information recorded in the operation process.
In another embodiment, the sensing unit provided at the construction site performs construction work weather, construction work scene, and construction progress data measurement and entry. For example: the working temperature is recorded by a temperature sensor, and the construction time is recorded by a sound sensor.
S306, acquiring engineering site image data based on the image acquisition unit.
In one scenario, the image acquisition unit includes one of an unmanned aerial vehicle configured with an image function, an image acquisition device provided at a construction site, a mobile app, and a camera, and the acquired engineering site picture data includes an overall environment image of the construction site, a near-far image of a building, and a measurement image of an area construction structure.
S308, denoising processing is performed on the image data based on the image processing unit.
Considering that a large amount of noise interference usually exists in a construction site, an image acquired based on the image acquisition unit is affected by the noise of the construction site, and the quality of image data is affected, so that the image data needs to be preprocessed before the on-site image data is integrated into a three-dimensional model, the image quality can be effectively improved, and the accuracy of a supervision analysis result is improved.
S310, building an engineering BIM model based on engineering supervision information and engineering site image data of a plurality of construction nodes.
The method comprises the steps of constructing a model constructed by the engineering BIM based on engineering supervision operation information and engineering site image data, integrating and supplementing the engineering supervision operation information and the engineering site image data, reflecting the actual condition of a construction site, avoiding site construction model distortion caused by unilateral data, and further providing effective data support for the output of supervision analysis results.
S106, determining model difference data based on a standard BIM model and an engineering BIM model;
s108, outputting a supervision analysis result based on the model difference data.
Fig. 4 is a schematic flow chart of denoising processing of image data based on an image processing unit in the present application, as shown in fig. 4, in one embodiment, denoising processing of image data based on the image processing unit includes:
s402, constructing a pair of training data set and verification data set according to the obtained image data and additive noise obtained by sampling in Gaussian distribution with known variance, and preprocessing the training data set.
S404, taking the convolutional neural network as a Boosting unit, and building a depth lifting frame model based on an SOS algorithm;
s406, training the depth lifting frame model by utilizing the preprocessed training data set, and adjusting corresponding model parameters.
And updating the parameters of the depth lifting framework model by using a random gradient descent algorithm by utilizing the preprocessed training data set until convergence.
S408, adjusting the structural super-parameters and the optimization super-parameters of the trained depth lifting frame model by using the verification data set; and verifying the depth lifting frame model by using the verification data set, and selecting the model parameter with the minimum recovery loss, thereby determining a final depth lifting frame model, and finally obtaining the field image data after the enhancement processing based on the depth lifting frame model.
The structural super-parameters comprise convolution kernel size and channel number, and the optimized super-parameters comprise learning rate and regularization loss coefficient.
According to the embodiment, the image noise reduction performance can be improved by optimizing parameters through the deep learning framework.
In one embodiment, constructing a training data set and a validation data set from the acquired image data and sampling additive noise in a gaussian distribution of known variance, and preprocessing the training data set comprises:
assuming that the acquired image data is a, the image data is distributed in a sigma gaussian distribution N (0, sigma 2 ) The additive noise V with the same resolution is obtained through the middle sampling;
adding noise V into a natural image A to obtain image data Y=A+V with noise, wherein Y in each pair of image data is used as the input of a depth lifting frame model, and A is used as a training target;
several sets of paired image data (Y, a) are collected, separated by a proportion, to form a training dataset D and a validation dataset V for redemption.
In one embodiment, the pretreatment method comprises: each pair of image data (y D ,x D ) Cutting to obtain a plurality of image blocks with the same resolution; then cut out y D And x D The obtained image blocks are respectively spliced into image batches with the same number of blocks and used for random gradient descent; finally, random amplification is performed within the image batch, including at least one of: 90 degree rotation, 180 degree rotation, 270 degree rotation, side-to-side rotation, and up-and-down mirroring.
In one embodiment, determining model difference data based on the standard BIM model and the engineering BIM model includes:
identifying difference data of a standard BIM model and an engineering BIM model based on a comparison unit, wherein the difference data comprises structure elevation difference data, space coordinate difference data, material difference data and progress difference data;
and outputting model difference data.
The model difference data comprises structure data, such as dimension difference data, engineering quantity difference data and material difference data, which are inconsistent with the standard BIM model and the engineering BIM model.
In one embodiment, determining model difference data based on the standard BIM model and the engineering BIM model includes:
comparing the difference data with a preset difference threshold value, and judging the difference degree;
and when the difference data exceeds a preset difference threshold, sending early warning information to terminal equipment of the supervision personnel.
And determining a difference threshold value corresponding to the difference data based on a preset difference rule, judging the difference length, and when the difference data exceeds the difference threshold value, indicating that the actual construction is at risk, and carrying out risk reminding, wherein supervision manpower can judge and process the site construction condition in time according to early warning information.
In one embodiment, outputting the proctorial analysis results based on the model difference data includes:
and establishing a deep reinforcement learning model, wherein the engineering design scheme comprises a construction quality standard data set, the construction data information comprises actual construction quality data, and the deep reinforcement learning model is used for determining an engineering supervision result of the construction node based on the construction quality standard data set, the actual construction quality data and the model difference data.
In one embodiment, the deep reinforcement learning model uses model difference data, a construction quality standard data set and actual construction quality data as environmental state information, uses a supervision analysis result as a decision target, and is further used for using the environmental state information as input of the deep reinforcement learning model, uses the decision target as output of the deep reinforcement learning model, and the action space of the deep reinforcement learning model contains engineering quality anomaly.
The input of the deep learning model includes observation of current construction nodes, model difference data, construction quality standard data and change of actual construction quality data along with time, and the short-term and long-term memory network can discover the connection among the model difference data, the construction quality standard data, the actual construction quality data and the time continuations.
Fig. 5 is a schematic structural diagram of a BIM-based engineering supervision system in the present application, as shown in fig. 5, and according to another aspect of the present application, there is further provided a BIM-based engineering supervision system, including:
the standard BIM module 61 is used for building a standard BIM model according to engineering design information, wherein the engineering design information comprises engineering design schemes, engineering design drawings and construction progress plans of a plurality of construction nodes;
the engineering BIM module 62 is used for constructing an engineering BIM module according to site construction information, wherein the engineering construction information comprises site construction data information of a current construction node;
a comparison module 63 for determining model difference data based on the standard BIM model and the engineering BIM model;
the processing module 64 is configured to output a supervision analysis result based on the model difference data.
The implementation principle of the embodiment is as follows:
the standard BIM module 61 builds a standard BIM model according to engineering design information, wherein the engineering design information comprises engineering design schemes, engineering design drawings and construction progress plans of a plurality of construction nodes;
the engineering BIM module 62 builds an engineering BIM module according to site construction information, wherein the engineering construction information comprises site construction data information of the current construction node; the comparison module 63 determines model difference data based on the standard BIM model and the engineering BIM model; the processing module 64 outputs the proctorial analysis results based on the model difference data. The engineering progress and the quality can be visually reflected through BIM model comparison, management staff can control the engineering quality and the engineering progress, and engineering management efficiency is improved.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The foregoing are all preferred embodiments of the present application, and are not intended to limit the scope of the present application in any way, therefore: all equivalent changes in structure, shape and principle of this application should be covered in the protection scope of this application.
Claims (10)
1. A method for engineering supervision based on BIM, comprising:
building a standard BIM model according to engineering design information, wherein the engineering design information comprises engineering design schemes, engineering design drawings and construction progress plans of a plurality of construction nodes;
building an engineering BIM module according to site construction information, wherein the engineering construction information comprises site construction data information of a current construction node;
determining model difference data based on the standard BIM model and the engineering BIM model;
and outputting a supervision analysis result based on the model difference data.
2. The engineering supervision method according to claim 1, wherein building a standard BIM model according to engineering design information includes:
engineering design scheme data are obtained, wherein the engineering design scheme data comprise engineering quantity data and construction scheme data of engineering, project construction operation flow and supply plans of material instruments;
engineering design drawing data are obtained, wherein the engineering design drawing data comprise engineering indoor and outdoor elevation drawing data, indoor and outdoor 3D effect drawing data, engineering plan drawing data and manufacturing standard information;
acquiring construction progress plan data, wherein the construction progress plan data comprises a construction progress plan of a construction project and a progress plan of a construction preparation stage;
and building the standard BIM model based on the engineering design scheme data, the engineering design drawing data and the construction progress plan data of a plurality of construction nodes.
3. The engineering supervision method according to claim 1, wherein the building the engineering BIM model according to the site construction information includes:
acquiring engineering supervision operation information;
acquiring site construction data based on the data acquisition unit;
acquiring engineering site image data based on an image acquisition unit;
denoising the image data based on the image processing unit;
and building the engineering BIM based on the engineering supervision operation information and the engineering field image data of a plurality of construction nodes.
4. The engineering supervision method according to claim 1, wherein the denoising processing of the image data based on the image processing unit includes:
constructing a pair of training data set and verification data set according to the obtained image data and sampling in Gaussian distribution with known variance to obtain additive noise, and preprocessing the training data set;
taking the convolutional neural network as a Boosting unit, and building a depth lifting frame model based on an SOS algorithm; training the depth lifting frame model by utilizing the preprocessed training data set, and adjusting corresponding model parameters;
adjusting the structural super-parameters and the optimization super-parameters of the trained depth lifting frame model by using the verification data set; and verifying the depth lifting frame model by using the verification data set, and selecting the model parameter with the minimum recovery loss, thereby determining a final depth lifting frame model, and finally obtaining the field image data after the enhancement processing based on the depth lifting frame model.
5. The engineering supervision method according to claim 4, wherein the constructing a pair of training data set and verification data set from the obtained image data and sampling additive noise in a gaussian distribution of known variance, and preprocessing the training data set includes:
assuming that the acquired image data is a, the image data is distributed in a sigma gaussian distribution N (0, sigma 2 ) The additive noise V with the same resolution is obtained through the middle sampling;
adding noise V into a natural image A to obtain image data Y=A+V with noise, wherein Y in each pair of image data is used as the input of a depth lifting frame model, and A is used as a training target;
several sets of paired image data (Y, a) are collected, separated by a proportion, to form a training dataset D and a validation dataset V for redemption.
6. The engineering supervision method according to claim 1, wherein the determining model difference data based on the standard BIM model and the engineering BIM model includes:
identifying difference data of the standard BIM model and the engineering BIM model based on a comparison unit, wherein the difference data comprises structure elevation difference data, space coordinate difference data, material difference data and progress difference data;
and outputting the model difference data.
7. The engineering supervision method according to claim 6, wherein the determining model difference data based on the standard BIM model and the engineering BIM model includes:
comparing the difference data with a preset difference threshold value, and judging the difference degree;
and when the difference data exceeds a preset difference threshold, sending early warning information to terminal equipment of the supervision personnel.
8. The engineering proctoring method of claim 1, wherein the outputting a proctoring analysis result based on the model difference data comprises:
and establishing a deep reinforcement learning model, wherein the engineering design scheme comprises construction quality standard data, the construction data information comprises actual construction quality data, and the deep reinforcement learning model is used for determining an engineering supervision result of the construction node based on the construction quality standard data, the actual construction quality data and model difference data.
9. The engineering supervision method according to claim 8, wherein the deep reinforcement learning model uses the model difference data, the construction quality standard data and the actual construction quality data as environmental state information, uses the supervision analysis result as a decision target, and is further used for using the environmental state information as an input of the deep learning model, uses the decision target as an output of the deep reinforcement learning model, and uses an action space of the deep reinforcement learning model to contain engineering quality anomalies.
10. A BIM-based engineering supervision system, comprising:
the standard BIM module is used for building a standard BIM model according to engineering design information, wherein the engineering design information comprises engineering design schemes, engineering design drawings and construction progress plans of a plurality of construction nodes;
the engineering BIM module is built according to site construction information, wherein the engineering construction information comprises site construction data information of the current construction node;
the comparison module is used for determining model difference data based on the standard BIM model and the engineering BIM model;
and the processing module is used for outputting a supervision analysis result based on the model difference data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310048414.0A CN116050772A (en) | 2023-01-31 | 2023-01-31 | Engineering supervision method and system based on BIM |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310048414.0A CN116050772A (en) | 2023-01-31 | 2023-01-31 | Engineering supervision method and system based on BIM |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116050772A true CN116050772A (en) | 2023-05-02 |
Family
ID=86132788
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310048414.0A Pending CN116050772A (en) | 2023-01-31 | 2023-01-31 | Engineering supervision method and system based on BIM |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116050772A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117236794A (en) * | 2023-11-10 | 2023-12-15 | 陕西兵咨建设咨询有限公司 | BIM-based engineering supervision information management method, system, medium and equipment |
-
2023
- 2023-01-31 CN CN202310048414.0A patent/CN116050772A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117236794A (en) * | 2023-11-10 | 2023-12-15 | 陕西兵咨建设咨询有限公司 | BIM-based engineering supervision information management method, system, medium and equipment |
| CN117236794B (en) * | 2023-11-10 | 2024-02-02 | 陕西兵咨建设咨询有限公司 | BIM-based engineering supervision information management method, system, medium and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109635511B (en) | High-rise residential district compulsory emission scheme generation design method for generating countermeasure network based on conditions | |
| CN111985567B (en) | Automatic pollution source type identification method based on machine learning | |
| CN109815904B (en) | Fire identification method based on convolutional neural network | |
| CN116050772A (en) | Engineering supervision method and system based on BIM | |
| CN112784403A (en) | Numerical simulation method for establishing jointed rock mass discrete element model based on point cloud data | |
| CN111476683A (en) | Building engineering construction optimization system based on BIM | |
| CN111241660B (en) | Civil engineering experiment detection system and method based on cloud computing technology | |
| Kabolizade et al. | Design and implementation of an algorithm for automatic 3D reconstruction of building models using genetic algorithm | |
| CN115730684A (en) | Air quality detection system based on LSTM-CNN model | |
| CN115062675A (en) | Full-spectrum pollution tracing method based on neural network and cloud system | |
| Yang et al. | A map‐algebra‐based method for automatic change detection and spatial data updating across multiple scales | |
| CN113360980A (en) | BIM technology-based deformed steel structure visualization construction method | |
| CN115439753A (en) | Steep river bank identification method and system based on DEM | |
| Xu et al. | Intelligent monitoring and residual analysis of tunnel point cloud data based on free-form approximation | |
| CN111429471A (en) | Geological disaster information management system and method | |
| CN111243088A (en) | True three-dimensional aerial remote sensing geological interpretation method and system in engineering geological investigation | |
| CN114693114A (en) | Monitoring method and device for underground space structure, computer equipment and storage medium | |
| CN115540752A (en) | Engineering quality allowable deviation detection system based on laser point cloud and construction method | |
| CN113761806B (en) | Atmospheric visibility prediction method based on neural network | |
| CN114268365B (en) | Communication optical cable intelligent early warning method and system based on visualization technology | |
| CN113919035A (en) | BIM and GIS-based electronic sand table construction method and system | |
| Yastikli et al. | Automatic 3D building model generations with airborne LiDAR data | |
| CN113409458A (en) | Lightweight real-scene three-dimensional model production method integrated with BIM design platform | |
| CN110795791A (en) | Engineering model slicing method and device, computer equipment and storage medium | |
| CN117668958B (en) | Coastline fractal dimension automatic calculation method, system and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |