CN116468392A

CN116468392A - Method, device, equipment and storage medium for monitoring progress of power grid engineering project

Info

Publication number: CN116468392A
Application number: CN202310391322.2A
Authority: CN
Inventors: 钟彬; 李冰若; 兰巧倩; 鲁静; 冯程; 费一涵; 何玉凤
Original assignee: State Grid Shanghai Electric Power Co Ltd; Yuanguang Software Co Ltd
Current assignee: State Grid Shanghai Electric Power Co Ltd; Yuanguang Software Co Ltd
Priority date: 2023-04-11
Filing date: 2023-04-11
Publication date: 2023-07-21

Abstract

The application discloses a method, a device, equipment and a storage medium for monitoring progress of a power grid project, and belongs to the technical field of artificial intelligence. According to the method, the construction information model is built according to the power grid project data, project site pictures of the power grid project are collected, target objects in the project site pictures are detected, image matching is conducted on the detected target objects and all objects to be constructed in the construction information model one by one, the project site pictures are embedded into the construction information model according to image matching results, the project progress model is generated, project construction progress data are extracted from the project progress model, and the project construction progress data are output. The project site live-action combined three-dimensional model is constructed by combining the building information model and the image processing technology, so that a user can conveniently and intuitively know the progress of the power grid project in real time, modeling data is uploaded by site live-action shooting, and accuracy and authenticity of the progress data are guaranteed.

Description

Method, device, equipment and storage medium for monitoring progress of power grid engineering project

Technical Field

The application belongs to the technical field of artificial intelligence, and particularly relates to a method, a device, equipment and a storage medium for monitoring progress of a power grid project.

Background

With the full utilization of BIM (Building Information Modeling, building information model) technology in the building field, digital design and digital delivery of power grid construction have become important components of infrastructure management; on the other hand, with the improvement of the engineering field information acquisition and analysis capability by artificial intelligence technology and 5G technology, the digital process in the power grid field is continuously accelerated.

However, the project monitoring system of the current power grid is collected through a capital construction information system, and project progress data is mainly filled manually by project managers of a construction department. Therefore, the accuracy and the authenticity of progress data filling mainly depend on the working quality of workers, but the project statistical caliber has deviation, the authenticity accuracy cannot be ensured, and the technical means for checking and rechecking are lacked. Because of index checking pressure, partial basic units even false report investment causes data distortion and increases project management risk.

In summary, from the construction conditions of the monitoring system and the online power grid in the engineering project of the current power grid, the problems of data statistical distortion, insufficient data value mining, and the like are existed, and the innovative application of the online power grid is to be enhanced.

Disclosure of Invention

The embodiment of the application aims to provide a power grid project progress monitoring method, a device, computer equipment and a storage medium, so as to solve the technical problems of insufficient data statistical distortion and data value mining of a monitoring system of a current power grid project.

In order to solve the above technical problems, the embodiments of the present application provide a method for monitoring progress of a power grid project, which adopts the following technical scheme:

a method for monitoring progress of a power grid project, comprising:

acquiring power grid project data, and constructing a building information model according to the power grid project data, wherein the building information model comprises a plurality of objects to be built of the power grid project;

acquiring project site pictures of power grid project, and detecting target objects in the project site pictures;

carrying out one-to-one image matching on the detected target object and all objects to be built in the building information model;

embedding the project site picture into the building information model according to the image matching result to generate an engineering project progress model;

and extracting project construction progress data from the project progress model, and outputting the project construction progress data.

Further, the collecting project site pictures of the power grid project and detecting target objects in the project site pictures specifically includes:

extracting image features of the project scene pictures, and carrying out feature marking on the image features;

embedding the project site picture with the feature marks into a pre-trained target detection model to obtain a target object in the project site picture;

before the image features of the project scene picture are extracted and the image features are marked, the method further comprises the following steps:

and carrying out preprocessing operation on the scene target picture, wherein the preprocessing operation comprises denoising processing, enhancement processing, restoration processing and segmentation processing.

Further, before the project site picture with the completed feature mark is embedded into a pre-trained target detection model to obtain a target object in the project site picture, the method further comprises:

acquiring a power grid engineering historical project picture, and carrying out feature marking on the power grid engineering project;

constructing a training data set by using the grid engineering historical project pictures with the completed feature marks;

training a preset image detection model through the training data set to obtain a target detection pre-training recognition result;

And carrying out iterative updating on the image detection model according to the target detection pre-training recognition result until the model is fitted, and generating a pre-trained target detection model.

Further, the step of iteratively updating the image detection model according to the target detection pre-training recognition result until the model is fitted, and the step of generating a pre-trained target detection model specifically includes:

comparing the target detection pre-training recognition result with a preset standard result, and calculating the recognition error of the image detection model;

comparing the identification error with a preset error threshold;

and when the identification error is greater than or equal to a preset error threshold, adjusting model parameters of the image detection model until the identification error is less than the preset error threshold, so as to obtain a pre-trained target detection model.

Further, the building information model is a BIM model, and after the acquiring the power grid project data and constructing the building information model according to the power grid project data, the building information model further includes:

and carrying out region segmentation on the building information model to obtain a civil engineering region sub-model, a transformation region sub-model and a wire inlet region sub-model of the power grid engineering project.

Further, the step of performing image matching on the detected target object and all objects to be built in the building information model one by one specifically includes:

carrying out image fuzzy matching on the target object and all objects to be built in the building information model through a fuzzy matching algorithm;

determining a target area where the target object is located according to an image fuzzy matching result, wherein the target area comprises a civil engineering area, a transformation area and an incoming line area;

and carrying out one-to-one image matching on the target object and all objects to be built in the sub-model of the target area.

Further, the step of performing image matching on the target object and all objects to be built in the sub-model of the target area one by one specifically includes:

comparing the target object with the feature points of the object to be built, and calculating feature similarity;

determining whether the target object is matched with the object to be built or not according to the feature similarity and a preset similarity threshold;

if the feature similarity is greater than or equal to a preset similarity threshold, the target object is matched with the object to be built;

embedding the project site picture into the building information model according to the image matching result to generate an engineering project progress model, which specifically comprises the following steps:

When the target object is matched with the object to be built, carrying out picture transformation on the project site picture where the target object is located, wherein the picture transformation comprises picture scaling and picture three-dimensional conversion;

and embedding the transformed project site pictures into the building information model to generate the project progress model.

In order to solve the technical problem, the embodiment of the application also provides a power grid project progress monitoring device, which adopts the following technical scheme:

a power grid project progress monitoring device, comprising:

the system comprises a model construction module, a model analysis module and a model analysis module, wherein the model construction module is used for acquiring power grid project data and constructing a building information model according to the power grid project data, wherein the building information model comprises a plurality of objects to be built of the power grid project;

the picture acquisition module is used for acquiring project site pictures of power grid project and detecting target objects in the project site pictures;

the image matching module is used for carrying out image matching on the detected target object and all objects to be built in the building information model one by one;

the picture embedding module is used for embedding the project field picture into the building information model according to the image matching result to generate an engineering project progress model;

And the progress monitoring module is used for extracting project construction progress data from the project progress model and outputting the project construction progress data.

In order to solve the above technical problems, the embodiments of the present application further provide a computer device, which adopts the following technical schemes:

a computer device comprising a memory having stored therein computer readable instructions which when executed by a processor implement the steps of the grid project progress monitoring method of any of the above claims.

In order to solve the above technical problems, embodiments of the present application further provide a computer readable storage medium, which adopts the following technical solutions:

a computer readable storage medium having stored thereon computer readable instructions which when executed by a processor implement the steps of the grid project progress monitoring method of any of the above claims.

Compared with the prior art, the embodiment of the application has the following main beneficial effects:

the application discloses a method, a device, equipment and a storage medium for monitoring progress of a power grid project, and belongs to the technical field of artificial intelligence. The method comprises the steps of obtaining power grid project data, constructing a building information model according to the power grid project data, wherein the building information model comprises a plurality of objects to be built of the power grid project, collecting project site pictures of the power grid project, detecting target objects in the project site pictures, performing one-to-one image matching on the detected target objects and all the objects to be built in the building information model, embedding the project site pictures into the building information model according to image matching results, generating an engineering project progress model, extracting project construction progress data from the engineering project progress model, and outputting the project construction progress data. The project site live-action combined three-dimensional model is constructed by combining the building information model and the image processing technology, so that a user can conveniently and intuitively know the progress of the power grid project in real time, modeling data is uploaded by site live-action shooting, and accuracy and authenticity of the progress data are guaranteed.

Drawings

For a clearer description of the solution in the present application, a brief description will be given below of the drawings that are needed in the description of the embodiments of the present application, it being obvious that the drawings in the following description are some embodiments of the present application, and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.

FIG. 1 illustrates an exemplary system architecture diagram in which the present application may be applied;

FIG. 2 illustrates a flow chart of one embodiment of a method of grid project progress monitoring according to the present application;

FIG. 3 shows a region segmentation map of a BIM three-dimensional model of a grid project progress monitoring method according to the present application;

FIG. 4 illustrates an unmanned aerial vehicle oblique photography image of a grid project progress monitoring method according to the present application;

FIG. 5 illustrates an image matching schematic of a grid project progress monitoring method according to the present application;

FIG. 6 illustrates a progress schematic of one embodiment of a power grid project progress monitoring method according to the present application;

FIG. 7 illustrates a progress schematic of another embodiment of a grid project progress monitoring method according to the present application;

FIG. 8 illustrates a structural schematic diagram of one embodiment of a grid project progress monitoring device according to the present application;

fig. 9 shows a schematic structural diagram of one embodiment of a computer device according to the present application.

Detailed Description

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the applications herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having" and any variations thereof in the description and claims of the present application and in the description of the figures above are intended to cover non-exclusive inclusions. The terms first, second and the like in the description and in the claims or in the above-described figures, are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.

In order to better understand the technical solutions of the present application, the following description will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings.

As shown in fig. 1, a system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various communication client applications, such as a web browser application, a shopping class application, a search class application, an instant messaging tool, a mailbox client, social platform software, etc., may be installed on the terminal devices 101, 102, 103.

The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablet computers, electronic book readers, MP3 players (Moving Picture Experts Group Audio Layer III, dynamic video expert compression standard audio plane 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic video expert compression standard audio plane 4) players, laptop and desktop computers, and the like.

The server 105 may be a server that provides various services, such as a background server that provides support for pages displayed on the terminal devices 101, 102, 103, and may be a stand-alone server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

It should be noted that, the method for monitoring the progress of the power grid project provided by the embodiment of the application is generally executed by a server, and accordingly, the device for monitoring the progress of the power grid project is generally arranged in the server.

It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

With continued reference to fig. 2, a flow chart of one embodiment of a method of grid project progress monitoring according to the present application is shown. The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.

Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.

The project entry monitoring system of the current power grid is collected through a capital construction information system, and project progress data is manually filled in by project managers of the construction department. Therefore, the accuracy and the authenticity of progress data filling mainly depend on the working quality of workers, but the project statistical caliber has deviation, the authenticity accuracy cannot be ensured, and the technical means for checking and rechecking are lacked. Because of index checking pressure, partial basic units even false report investment causes data distortion and increases project management risk.

The application discloses a method, a device, equipment and a storage medium for monitoring the progress of a power grid project, belongs to the technical field of artificial intelligence, constructs a project site live-action combined three-dimensional model by combining a building information model and an image processing technology, facilitates a user to know the progress of the power grid project in real time and intuitively, and modeling data is uploaded by adopting site live-action shooting, so that the accuracy and the authenticity of the progress data are ensured.

The power grid project progress monitoring method comprises the following steps:

s201, acquiring power grid project data, and constructing a building information model according to the power grid project data, wherein the building information model comprises a plurality of objects to be built of the power grid project.

In this embodiment, after receiving the power grid project progress monitoring instruction, the server acquires power grid project data, and constructs a building information model according to the power grid project data, where the building information model includes a plurality of objects to be built of the power grid project, for example, a substation civil engineering facility, a cable, a transformer, and the like.

The building information model is a BIM model, BIM is an abbreviation of Building Information Modeling (building information modeling), and is a digitalized building design and management method. The BIM model is a digital three-dimensional building model, and can integrate various information such as building geometry, construction, engineering, maintenance and the like. BIM model can help architects, engineers, constructors and owners to cooperate better in building design and construction process, raise efficiency and quality. The BIM model can provide various data and information such as the size, material, cost, construction period, construction order, etc. of the building elements, as well as visual building models and animations. The BIM model can improve the efficiency and quality of the building in the life cycle of the whole building project, reduce errors and repeated work, reduce cost and improve safety and sustainability.

In this embodiment, the electronic device (such as the server shown in fig. 1) on which the power grid project progress monitoring method operates may receive various instructions and data through a wired connection manner or a wireless connection manner. It should be noted that the wireless connection may include, but is not limited to, 3G/4G connections, wiFi connections, bluetooth connections, wiMAX connections, zigbee connections, UWB (ultra wideband) connections, and other now known or later developed wireless connection means.

Further, after acquiring the power grid project data and constructing the building information model according to the power grid project data, the method further comprises the following steps:

and carrying out region segmentation on the building information model to obtain a civil engineering region sub-model, a transformation region sub-model and a line incoming region sub-model of the power grid engineering project.

In this embodiment, the server integrates with a digital Building Information Modeling (BIM) system, and analyzes the BIM three-dimensional model according to the space to obtain a region sub-model of each space, and performs region division on the power grid building project, and the method is divided into three parts of civil engineering, transformation and line incoming. As shown in fig. 3, the civil engineering part of the BIM model is divided, and the BIM model is divided into three areas of 1 layer underground, 1 layer civil engineering and 2 layers civil engineering according to the actual condition of the civil engineering. And the power transformation part of the BIM model is divided, and the BIM model is divided into six independent spaces of a main transformer, a cable layer, a GIS room, a switch room, a reactive compensation area and a secondary equipment room according to the actual power transformation situation. And (3) dividing the incoming line part of the BIM model, wherein the incoming line part is divided according to the tower serving as a datum point.

BIM model construction, namely acquiring a BIM model RVT 2018 format file manufactured by the reverser software in a digital infrastructure (BIM) system in an integrated mode, and constructing a BIM three-dimensional model of the project in the system. And (3) carrying out the modularization of the segmentation part according to different voltage levels, item types and single engineering types of the items to form a BIM model component resource library, and providing basic component support for the convenient construction and display of the BIM model.

In the above embodiment, the present application constructs and performs region segmentation on the BIM model through the BIM model, so as to intuitively understand the engineering progress conditions of civil engineering, power transformation and line incoming later.

S202, acquiring project site pictures of the power grid project, and detecting target objects in the project site pictures.

In this embodiment, after completing building a BIM model and performing region segmentation on the BIM model, the server collects project field pictures of the power grid project, detects target objects in the project field pictures, and aims to embed the project field pictures into the BIM model through object matching so as to build a real construction progress image model on site.

The method comprises the steps of obtaining indoor and outdoor real-time construction instant images of a project site through technologies such as on-site photo taking, video monitoring, unmanned aerial vehicle oblique photography, intelligent statistical robot three-dimensional laser scanning and the like. The photo acquisition is carried out by taking a picture through a field mobile phone to acquire the condition of a construction field; the video monitoring is carried out in a video monitoring mode, so that on-site real-time images are obtained in real time; unmanned aerial vehicle oblique photography obtains a three-dimensional image by adopting unmanned aerial vehicle aerial oblique photography technology, as shown in fig. 4; the intelligent statistical robot is used for carrying a three-dimensional laser scanner through an indoor track laying robot and periodically acquiring on-site accurate three-dimensional coordinate information and indoor construction condition information of project engineering.

Further, collecting project site pictures of the power grid project, and detecting target objects in the project site pictures, wherein the method specifically comprises the following steps:

extracting image features of the project field pictures, and carrying out feature marking on the image features;

embedding the project site picture with the feature mark into a pre-trained target detection model to obtain a target object in the project site picture;

before extracting the image features of the project scene picture and carrying out feature marking on the image features, the method further comprises the following steps:

and carrying out preprocessing operation on the target field picture, wherein the preprocessing operation comprises denoising processing, enhancement processing, restoration processing and segmentation processing.

In this embodiment, a target detection scheme based on feature markers is used, which includes the following two main steps:

1. extracting image features and marking the features. This step is to capture key information in the image and encode it into a form that can be processed by machine learning algorithms, typically using Convolutional Neural Networks (CNNs) or other deep learning models to extract image features, feature labels meaning the addition of semantic tags to the extracted image features so that the subsequent object detection model can understand the meaning represented by these features.

2. Embedding the target detection model and detecting the target object. The image after the feature marking is input into a pre-trained target detection model, and the model extracts the position and category information of the target object from the image. The object detection model is typically implemented using an algorithm such as a region-based convolutional neural network (R-CNN), a single-stage detector (YOLO, SSD), or a two-stage detector (Faster R-CNN).

In the embodiment, the method and the device can effectively process images with different sizes and complexity and have higher target detection precision by extracting the image characteristics of the project field pictures, carrying out characteristic marking on the image characteristics and utilizing the pre-trained target detection model to realize target detection of the project field pictures.

In this embodiment, a preprocessing operation is also required for the destination field picture before the target detection is performed, wherein the preprocessing operation includes a denoising process, an enhancement process, a restoration process, and a segmentation process.

The denoising processing is used for removing noise interference in the image and improving the quality and definition of the image. Some filters, such as gaussian filters, median filters, etc., are typically employed. The enhancement processing is to enhance the contrast, brightness, etc. of the image, so that the image is clearer. Common enhancement processing algorithms include histogram equalization, contrast enhancement, and the like. The restoration process is to repair distorted or damaged portions in the image, improving the sharpness and readability of the image. Typically implemented using some image restoration algorithms such as wiener filtering, laplacian pyramids, etc. The segmentation process is to divide the image into different regions or objects for better subsequent processing. Typically implemented using some image segmentation algorithms, such as threshold segmentation, region-based segmentation, etc. The image quality can be improved by preprocessing, so that the subsequent processing is more accurate and fine.

Further, before embedding the project site picture with the feature mark into the pre-trained target detection model to obtain the target object in the project site picture, the method further comprises the following steps:

training a preset image detection model through a training data set to obtain a target detection pre-training recognition result;

In this embodiment, before image target detection, a target detection model needs to be trained in advance, and specific training steps are as follows:

and acquiring a power grid engineering historical project picture and carrying out characteristic marking. This step is to extract key information in the picture, typically using Convolutional Neural Networks (CNNs) or other deep learning models for feature extraction, and then labeling the extracted image features so that the subsequent training process can recognize and understand the meaning represented by these features.

A training dataset is constructed. And forming a training data set by the history item pictures with the completed feature marks and the corresponding labeling data, and training a target detection model.

And training a target detection model. And inputting the constructed training data set into a preset target detection model for training, and outputting a target detection result really aiming at the training data set by the model according to the input picture and the annotation data.

And iteratively updating the model. And iteratively updating the model according to the target detection pre-training recognition result to improve the accuracy and generalization capability of the model until the model is fitted to generate a pre-trained target detection model.

In the embodiment, the method and the device can utilize the historical project pictures to carry out model training, avoid a large amount of manual labeling work and improve efficiency. Meanwhile, the model is updated through iteration, so that the accuracy and the robustness of the model can be gradually improved.

Further, the image detection model is iteratively updated according to the target detection pre-training recognition result until the model is fitted, so as to generate a pre-trained target detection model, which specifically comprises the following steps:

Comparing the identification error with a preset error threshold;

and when the recognition error is greater than or equal to a preset error threshold, adjusting model parameters of the image detection model until the recognition error is less than the preset error threshold, and obtaining the pre-trained target detection model.

Comparing the target object identified by the pre-training model with a preset standard result, wherein the preset standard result is a marked power grid engineering historical project picture, so as to obtain the identification error of the model, evaluating the identification accuracy of the model by calculating an error index of the model, such as an average absolute error (MAE) or a Mean Square Error (MSE), comparing the calculated identification error with a preset error threshold value, judging whether the model meets the preset identification accuracy requirement, and when the identification error of the model is greater than or equal to the preset error threshold value, adjusting the model parameters of the model to improve the identification accuracy of the model, and repeating the steps until the identification error is smaller than the preset error threshold value, so as to obtain the pre-trained target detection model.

In the above embodiment, the present application gradually optimizes the model by repeating the processes of comparing, calculating the error and adjusting the model parameters until reaching the preset recognition accuracy requirement, thereby obtaining the pre-trained target detection model. According to the scheme, the error threshold can be set according to actual requirements, and the recognition accuracy of the model is gradually improved by repeatedly optimizing model parameters, so that the preset requirements are met.

And S203, performing one-to-one image matching on the detected target object and all objects to be built in the building information model.

In the above embodiment, after finishing target detection of the project site picture, the server performs image matching on the detected target object and all objects to be built in the building information model one by one, so as to embed the project site picture into the building information model according to the image matching result, and generate the actual building progress image model on site.

Further, image matching is carried out on the detected target object and all objects to be built in the building information model one by one, and the method specifically comprises the following steps:

determining a target area where a target object is located according to an image fuzzy matching result, wherein the target area comprises a civil engineering area, a transformation area and an incoming line area;

and performing one-to-one image matching on the target object and all objects to be built in the sub-model of the target area.

In this embodiment, as shown in fig. 5, the server performs image fuzzy matching on the target object and all objects to be built in the building information model through a fuzzy matching algorithm, and determines a target area where the target object is located according to an image fuzzy matching result, where the target area includes a civil engineering area, a transformation area and an incoming line area, and then performs image matching on the target object and all objects to be built in a sub-model of the target area one by one.

Fuzzy matching is a data preliminary matching technique for comparing two or more records and calculating the likelihood that they belong to the same entity. Fuzzy matching does not generally classify records as matching and not matching, but rather outputs a number (typically between 0-100) for identifying the likelihood that the records belong to the same customer, product, employee, etc. Efficient fuzzy matching algorithms can handle a range of data ambiguities such as first/last name inversion, acronyms, shortened names, pinyin and intentional misspellings, abbreviations, add/delete punctuation, etc.

The implementation of the above image matching step may be implemented based on one or a combination of SIFT (scale invariant feature transform) algorithm, SURF (accelerated robust features) algorithm or ORB (oriented fast and rotational presentation) algorithm.

In the embodiment, the image matching is firstly performed, the target area where the target object is located is determined, and then the image matching is performed on the target object and the objects to be built in the submodel of the target area one by one on the basis of the image fuzzy matching, so that the accuracy of the image matching is ensured, the data operation amount is reduced, and the computing resource is saved.

Further, image matching is carried out on the target object and all objects to be built in the sub-model of the target area one by one, and the method specifically comprises the following steps:

comparing the target object with the feature points of the object to be built, and calculating the feature similarity;

if the feature similarity is greater than or equal to a preset similarity threshold, the target object is matched with the object to be built.

In this embodiment, SIFT, SURF, and ORB algorithms are used to extract feature points of a target object, where each feature point contains one piece of position, scale, and direction information, and describes its local texture feature with one vector. And matching the characteristic points of the target object with the characteristic points of all objects to be built in the matched target region submodel, calculating the similarity between the characteristic points by adopting a distance-based method, such as Euclidean distance or Hamming distance, and the like, and selecting a plurality of characteristic points with highest similarity as matching points according to similarity sorting. The matching of the two-dimensional image coordinates and the three-dimensional space coordinates can be realized through the corresponding relation between the position information of the matching points and the space position information of the object to be built in the building information model, and the two-dimensional image coordinates can be converted into the three-dimensional space coordinates by using methods such as camera calibration. And combining the three-dimensional coordinate information of the object to be built in the building information model which is successfully matched, so as to obtain the three-dimensional model of the whole project. Three-dimensional modeling software such as 3DGIS, sketchUp, 3ds Max, etc. can be used to construct the three-dimensional model and import the matching results into the software for editing and modification.

In a specific embodiment of the present application, it is assumed that there is a picture a in a building information model, which needs to be matched with a project site picture B to build a three-dimensional model. Extracting feature points and descriptors from the pictures A and B by using SIFT, SURF and ORB algorithms respectively to obtain feature point sets and feature vector sets of the two pictures, performing similarity matching on the feature vector sets of the pictures A and B to obtain an optimal matching point set, converting two-dimensional image coordinates of the matching point set into three-dimensional space coordinates by using methods such as camera calibration, combining three-dimensional space coordinate information of the matching point set, modeling by using a 3DGIS model, and establishing a three-dimensional model of the whole project. Of course, in practical application, the problems of influence of factors such as picture noise, illumination change and the like on matching precision, quality evaluation of a matching point set, error correction and the like also need to be considered.

In the above embodiment, registration learning is performed by performing contrast analysis on a large number of images, feature points are extracted to obtain feature points, matching feature point pairs are found by performing similarity measurement, then image space coordinate transformation parameters are obtained by the matching feature point pairs, and finally image registration is performed by the coordinate transformation parameters. The management requirements of the power grid project construction nodes in the construction part and the development part are combined, the collected progress information, namely the site construction pictures, are abstracted, the collected site construction pictures and the BIM model are subjected to image recognition through image registration learning to automatically conduct embedded matching, then the 3DGIS model is matched for modeling, the site actual construction progress model is constructed in regions, and a foundation is provided for image recognition and artificial intelligence judgment progress.

S204, embedding the project site pictures into the building information model according to the image matching result to generate an engineering project progress model.

In this embodiment, after image matching, the server has determined the relationship between the target object in the project field picture and the object to be built of the building information model, then matches the two-dimensional image coordinate and the three-dimensional space coordinate, converts the two-dimensional image coordinate into the three-dimensional space coordinate, and models with the 3DGIS model, and constructs the project progress model in regions, where the project progress model is the field actual construction progress model of the power grid project, and the field actual construction progress of the current power grid project can be intuitively known through the model.

The on-site actual construction progress digital conversion is carried out on the on-site collected images by the artificial intelligence technology according to the on-site actual construction information and the on-site actual construction progress image model of each area of the BIM model, the on-site actual construction information of each project and the on-site condition of equipment are collected in real time by means of the image recognition technology, and the actual construction progress of each voltage grade, each project category, each project and each main body node is obtained.

Embedding project site pictures into a building information model according to an image matching result to generate an engineering project progress model, which specifically comprises the following steps:

embedding the transformed project site pictures into a building information model to generate an engineering project progress model.

When the picture transformation of the project site picture is carried out, the matching of the two-dimensional image coordinate and the three-dimensional space coordinate can be realized through the corresponding relation between the position information of the matching point and the space position information of the object to be built in the building information model, and the picture scaling and the picture three-dimensional transformation can be carried out by using methods such as camera calibration, so that the two-dimensional image coordinate can be converted into the three-dimensional space coordinate, and the modeling of the 3DGIS model can be carried out later.

In the embodiment, project site information is completely collected by means of a real-time image recognition technology, a BIM model is combined to perform three-dimensional modeling on a construction site by means of photo collection, video monitoring, unmanned aerial vehicle oblique photography, intelligent statistical robots and the like on coordinates given by the BIM, a site image recognition intelligent application is constructed, video information modeling and model structuring are achieved, and therefore statistical analysis and digitization are further achieved.

S205, project construction progress data is extracted from the project progress model, and the project construction progress data is output.

In the embodiment, the server utilizes the space statistical model to convert the data in the project progress model into digital conversion, extracts project construction progress data, outputs the project construction progress data, completes intelligent development of the progress, and facilitates the user to check.

In a specific embodiment of the present application, please refer to fig. 6 and 7, taking a certain power transmission and transformation project such as 110 kv, 220 kv, 500 kv, etc. as an example, the power transmission and transformation project is divided into three parts of power transformation, civil engineering and wire incoming according to a single project, where the power transformation part is divided into 6 subspaces, which are respectively a reactive power compensation device room, a GIS room, a cable layer, a secondary equipment room, a power distribution device room and a main transformer room.

Taking 220 KV power transmission and transformation engineering as an example, the space of a reactive power compensation device room, a GIS room, a cable layer, a secondary equipment room, a distribution device room and a main transformer room is respectively 4.37%, 43.76%, 7%, 21.35%, 1.91% and 22% of investment completion ratio.

The civil engineering space is divided into four parts of exterior wall decoration, zero meter layer, overground one layer and structure capping, and is matched with a 3DGIS model.

Each space investment is 30% of zero meter layer, 20% of ground one layer, 20% of structure capping and 30% of outer wall decoration, wherein:

Overhead line engineering, which divides a space model into two parts of an upright rod and an overhead line; wherein, the investment completion ratio of the vertical rod is 40% and the overhead line is 60%. Wherein, the investment calculation model is accomplished to pole setting: pole setting completion investment = 40% x total investment x number of pole setting completed/total number of poles; overhead investment = 60% xtotal investment x length of overhead line/total length.

The calandria engineering, the space model is the worker well, the calandria engineering is accomplished investment calculation model and is: calandria engineering complete investment = total investment x number of completed wells/total number of wells.

And (3) cable engineering, wherein the space model is the cable laying length. Cabling project complete investment = total investment x complete cabling length/total cabling length.

In the embodiment, project site live-action combined three-dimensional model construction is performed on the whole power grid construction project, project construction progress data are extracted by using the space statistical model, and different space models are formed to correspond to different project completion progress.

In the above embodiment, the application discloses a power grid project progress monitoring method, and belongs to the technical field of artificial intelligence. The method comprises the steps of obtaining power grid project data, constructing a building information model according to the power grid project data, wherein the building information model comprises a plurality of objects to be built of the power grid project, collecting project site pictures of the power grid project, detecting target objects in the project site pictures, performing one-to-one image matching on the detected target objects and all the objects to be built in the building information model, embedding the project site pictures into the building information model according to image matching results, generating an engineering project progress model, extracting project construction progress data from the engineering project progress model, and outputting the project construction progress data. The project site live-action combined three-dimensional model is constructed by combining the building information model and the image processing technology, so that a user can conveniently and intuitively know the progress of the power grid project in real time, modeling data is uploaded by site live-action shooting, and accuracy and authenticity of the progress data are guaranteed.

On the other hand, the method and the device are also aimed at the technical problems that a plurality of enterprises focus on investment completion scale for investment statistics, have insufficient relevance with project starting, material receiving, equipment approach, power transformation construction and the like, are difficult to match with the progress of engineering milestones, and reduce the application value of investment statistics data.

In this embodiment, the construction of the investment completion model obtains the actual construction progress according to the embedded model generated by the 3DGIS model and the BIM model, obtains the corresponding BIM segmentation space for three-dimensional design analysis according to the information of the voltage level, the item type, the single engineering and the like of the item, sets the investment duty ratio of each space according to the actual situation, combines the space matching progress, determines the current month investment completion value, constructs the investment completion model, and realizes the automatic generation of the investment completion value.

And comparing the theoretical investment value generated by the cascade neural network investment progress model with the investment completion value automatically generated by the investment completion model. The past historical data are checked and analyzed to obtain the deviation early warning of different voltage grades, different project types and different single projects, manual repair and calibration are allowed in a threshold range, the fault tolerance of the system is improved, and the automatic investment of the system is more accurate and reasonable.

And the actual completion condition of the engineering is calculated by combining the staged panoramic image and the field live-action three-dimensional model and comparing the staged panoramic image and the field live-action three-dimensional model with the BIM progress model, so that the engineering progress is accurately monitored. The method is characterized in that project site information is acquired in real time and completely by means of an image recognition technology, site acquisition data, investment plans and capital construction digital information are automatically and intelligently checked, verified and analyzed by means of an artificial intelligence technology, video information modeling and model structuring are achieved, a complete power transmission and transformation engineering digital information base is built, a three-dimensional space model of virtual reality and actual investment completion amount are deduced, and statistical analysis digitization and intelligent analysis are further carried out.

And (3) aiming at on-site actual construction progress data formed by on-site live-action combined three-dimensional model artificial intelligence statistics, building power grid infrastructure project deviation early warning models with different voltage levels and engineering types by combining with BIM model construction progress, determining a checking scheme and setting an early warning threshold. The automatic investment completion progress and on-site investment progress acquisition value deviation early warning model is used for establishing different voltage levels and engineering type early warning model thresholds according to past year historical data by acquiring the investment completion progress in the investment completion model and the investment completion progress acquisition value acquired according to the actual construction progress in the construction management and control, and checking and analyzing the two to realize deviation early warning of projects; the method comprises the steps of acquiring a theoretical investment progress of an investment plan issued by a cascade neural network and an automatically generated investment progress, building early warning model thresholds of different voltage levels and engineering types according to past year history data, and performing check analysis on the theoretical investment progress and the automatically generated investment progress of the investment plan issued by the cascade neural network to realize early warning; and (3) carrying out early warning on the deviation of the material receiving progress in the ERP receiving information and the actual construction progress, establishing early warning model thresholds of different voltage levels and engineering types according to past year historical data by acquiring the on-site actual receiving progress of the material receiving progress and the real scene combined three-dimensional model of the ERP, and carrying out checking analysis on the two to realize early warning.

And checking and analyzing the automatically generated investment progress, actual construction progress and foundation management and control construction progress by depending on a power grid foundation construction deviation early warning model, carrying out early warning on the deviation of the material receiving progress with ERP receiving information, realizing digital statistical analysis on power grid foundation construction project plan execution, automatically generating a report, carrying out digital monitoring, and automatically monitoring and early warning abnormal progress of each level project.

It should be emphasized that, to further ensure the privacy and security of the above-mentioned grid project data, the above-mentioned grid project data may also be stored in a node of a blockchain.

The blockchain referred to in the application is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.

Those skilled in the art will appreciate that implementing all or part of the processes of the methods of the embodiments described above may be accomplished by way of computer readable instructions, stored on a computer readable storage medium, which when executed may comprise processes of embodiments of the methods described above. The storage medium may be a nonvolatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a random access Memory (Random Access Memory, RAM).

It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.

With further reference to fig. 8, as an implementation of the method shown in fig. 2, the present application provides an embodiment of a power grid project progress monitoring apparatus, where an embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be specifically applied to various electronic devices.

As shown in fig. 8, the power grid project progress monitoring device 800 according to the present embodiment includes:

the model construction module 801 is configured to obtain power grid project data, and construct a building information model according to the power grid project data, where the building information model includes a plurality of objects to be built of the power grid project;

The picture acquisition module 802 is used for acquiring project site pictures of power grid project and detecting target objects in the project site pictures;

the image matching module 803 is configured to perform image matching on the detected target object and all objects to be built in the building information model one by one;

the picture embedding module 804 is configured to embed the project field picture into the building information model according to the image matching result, and generate an engineering project progress model;

the progress monitoring module 805 is configured to extract project construction progress data from the project progress model, and output the project construction progress data.

Further, the image capturing module 802 specifically includes:

the feature marking unit is used for extracting image features of the project field pictures and marking the image features;

the target detection unit is used for embedding the project field picture with the completed feature mark into a pre-trained target detection model to obtain a target object in the project field picture;

the power grid project progress monitoring device 800 further includes:

the preprocessing module is used for preprocessing the on-site picture, wherein the preprocessing operation comprises denoising, enhancement, restoration and segmentation.

Further, the power grid project progress monitoring apparatus 800 further includes:

the historical data acquisition module is used for acquiring a power grid engineering historical project picture and carrying out characteristic marking on the power grid engineering project;

the training set construction module is used for constructing a training data set by using the grid engineering historical project pictures with the completed feature marks;

the model training module is used for training a preset image detection model through the training data set to obtain a target detection pre-training recognition result;

and the model iteration module is used for carrying out iteration update on the image detection model according to the target detection pre-training recognition result until the model is fitted, so as to generate a pre-trained target detection model.

Further, the model iteration module specifically includes:

the error calculation unit is used for comparing the target detection pre-training recognition result with a preset standard result and calculating the recognition error of the image detection model;

the error comparison unit is used for comparing the identification error with a preset error threshold value;

and the model iteration unit is used for adjusting model parameters of the image detection model when the recognition error is greater than or equal to a preset error threshold value until the recognition error is less than the preset error threshold value, so as to obtain a pre-trained target detection model.

Further, the building information model is a BIM model, and the power grid project progress monitoring device further comprises:

the regional segmentation module is used for carrying out regional segmentation on the building information model to obtain a civil engineering regional sub-model, a transformation regional sub-model and a line incoming regional sub-model of the power grid engineering project.

Further, the image matching module 803 specifically includes:

the fuzzy matching unit is used for carrying out image fuzzy matching on the target object and all objects to be built in the building information model through a fuzzy matching algorithm;

the area determining unit is used for determining a target area where the target object is located according to the image fuzzy matching result, wherein the target area comprises a civil engineering area, a transformation area and an incoming line area;

and the image matching unit is used for carrying out one-to-one image matching on the target object and all objects to be built in the sub-model of the target area.

Further, the image matching unit specifically includes:

the similarity calculation subunit is used for comparing the characteristic points of the target object and the object to be built and calculating the characteristic similarity;

the matching judging subunit is used for determining whether the target object is matched with the object to be built or not according to the feature similarity and a preset similarity threshold;

The judging result subunit is used for matching the target object with the object to be built when the feature similarity is greater than or equal to a preset similarity threshold value;

the picture embedding module 804 specifically includes:

the picture transformation unit is used for carrying out picture transformation on the project site picture where the target object is located when the target object is matched with the object to be built, wherein the picture transformation comprises picture scaling and picture three-dimensional conversion;

and the picture embedding unit is used for embedding the transformed project field picture into the building information model to generate an engineering project progress model.

In the embodiment, the application discloses a power grid engineering project progress monitoring device, and belongs to the technical field of artificial intelligence. The method comprises the steps of obtaining power grid project data, constructing a building information model according to the power grid project data, wherein the building information model comprises a plurality of objects to be built of the power grid project, collecting project site pictures of the power grid project, detecting target objects in the project site pictures, performing one-to-one image matching on the detected target objects and all the objects to be built in the building information model, embedding the project site pictures into the building information model according to image matching results, generating an engineering project progress model, extracting project construction progress data from the engineering project progress model, and outputting the project construction progress data. The project site live-action combined three-dimensional model is constructed by combining the building information model and the image processing technology, so that a user can conveniently and intuitively know the progress of the power grid project in real time, modeling data is uploaded by site live-action shooting, and accuracy and authenticity of the progress data are guaranteed.

In order to solve the technical problems, the embodiment of the application also provides computer equipment. Referring specifically to fig. 9, fig. 9 is a basic structural block diagram of a computer device according to the present embodiment.

The computer device 9 comprises a memory 91, a processor 92, a network interface 93 communicatively connected to each other via a system bus. It should be noted that only computer device 9 having components 91-93 is shown in the figures, but it should be understood that not all of the illustrated components are required to be implemented and that more or fewer components may be implemented instead. It will be appreciated by those skilled in the art that the computer device herein is a device capable of automatically performing numerical calculations and/or information processing in accordance with predetermined or stored instructions, the hardware of which includes, but is not limited to, microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASICs), programmable gate arrays (fields-Programmable Gate Array, FPGAs), digital processors (Digital Signal Processor, DSPs), embedded devices, etc.

The computer equipment can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing equipment. The computer equipment can perform man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch pad or voice control equipment and the like.

The memory 91 includes at least one type of readable storage medium including flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the storage 91 may be an internal storage unit of the computer device 9, such as a hard disk or a memory of the computer device 9. In other embodiments, the memory 91 may also be an external storage device of the computer device 9, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the computer device 9. Of course, the memory 91 may also comprise both an internal memory unit of the computer device 9 and an external memory device. In this embodiment, the memory 91 is generally used to store an operating system and various application software installed on the computer device 9, such as computer readable instructions of a power grid project progress monitoring method. Further, the memory 91 may be used to temporarily store various types of data that have been output or are to be output.

The processor 92 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 92 is typically used to control the overall operation of the computer device 9. In this embodiment, the processor 92 is configured to execute computer readable instructions stored in the memory 91 or process data, such as computer readable instructions for executing the grid project progress monitoring method.

The network interface 93 may comprise a wireless network interface or a wired network interface, which network interface 93 is typically used to establish a communication connection between the computer device 9 and other electronic devices.

In the above embodiment, the application discloses a computer device, which belongs to the technical field of artificial intelligence. The method comprises the steps of obtaining power grid project data, constructing a building information model according to the power grid project data, wherein the building information model comprises a plurality of objects to be built of the power grid project, collecting project site pictures of the power grid project, detecting target objects in the project site pictures, performing one-to-one image matching on the detected target objects and all the objects to be built in the building information model, embedding the project site pictures into the building information model according to image matching results, generating an engineering project progress model, extracting project construction progress data from the engineering project progress model, and outputting the project construction progress data. The project site live-action combined three-dimensional model is constructed by combining the building information model and the image processing technology, so that a user can conveniently and intuitively know the progress of the power grid project in real time, modeling data is uploaded by site live-action shooting, and accuracy and authenticity of the progress data are guaranteed.

The present application also provides another embodiment, namely, a computer readable storage medium, where computer readable instructions are stored, where the computer readable instructions are executable by at least one processor to cause the at least one processor to perform the steps of the grid project progress monitoring method as described above.

In the above embodiments, the application discloses a storage medium, which belongs to the technical field of artificial intelligence. The method comprises the steps of obtaining power grid project data, constructing a building information model according to the power grid project data, wherein the building information model comprises a plurality of objects to be built of the power grid project, collecting project site pictures of the power grid project, detecting target objects in the project site pictures, performing one-to-one image matching on the detected target objects and all the objects to be built in the building information model, embedding the project site pictures into the building information model according to image matching results, generating an engineering project progress model, extracting project construction progress data from the engineering project progress model, and outputting the project construction progress data. The project site live-action combined three-dimensional model is constructed by combining the building information model and the image processing technology, so that a user can conveniently and intuitively know the progress of the power grid project in real time, modeling data is uploaded by site live-action shooting, and accuracy and authenticity of the progress data are guaranteed.

From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk), comprising several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method described in the embodiments of the present application.

The subject application is operational with numerous general purpose or special purpose computer system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

It is apparent that the embodiments described above are only some embodiments of the present application, but not all embodiments, the preferred embodiments of the present application are given in the drawings, but not limiting the patent scope of the present application. This application may be embodied in many different forms, but rather, embodiments are provided in order to provide a more thorough understanding of the present disclosure. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described in the foregoing, or equivalents may be substituted for elements thereof. All equivalent structures made by the specification and the drawings of the application are directly or indirectly applied to other related technical fields, and are also within the protection scope of the application.

Claims

1. The utility model provides a power grid project progress monitoring method which is characterized by comprising the following steps:

2. The method for monitoring progress of a power grid project according to claim 1, wherein the steps of collecting a project field picture of the power grid project and detecting a target object in the project field picture comprise:

3. The method for monitoring progress of a power grid project according to claim 2, further comprising, before embedding the project site picture with the completed feature tag into a pre-trained target detection model to obtain a target object in the project site picture:

4. The method for monitoring progress of a power grid project according to claim 3, wherein the step of iteratively updating the image detection model according to the target detection pre-training recognition result until the model is fitted, and the step of generating the pre-trained target detection model specifically comprises the following steps:

Comparing the identification error with a preset error threshold;

5. The method for monitoring progress of a power grid project according to claim 2, wherein the building information model is a BIM model, and after the obtaining power grid project data and constructing the building information model according to the power grid project data, the method further comprises:

6. The method for monitoring progress of power grid engineering projects according to claim 5, wherein the step of performing image matching on the detected target object and all objects to be built in the building information model one by one specifically comprises the following steps:

7. The method for monitoring progress of power grid engineering projects according to claim 6, wherein the step of performing image matching on the target object and all objects to be built in the sub-model of the target area one by one specifically comprises:

8. The utility model provides a power grid engineering project progress monitoring device which characterized in that includes:

9. A computer device comprising a memory and a processor, the memory having stored therein computer readable instructions which when executed by the processor implement the steps of the grid project progress monitoring method of any of claims 1 to 7.

10. A computer readable storage medium having stored thereon computer readable instructions which when executed by a processor implement the steps of the grid project progress monitoring method of any of claims 1 to 7.