In this article, we review the digital twins of electrical equipment in smart grids to promote technological innovation in electrical equipment monitoring. This article provides an overview of the current development status of image 3D reconstruction and its application in 3D modeling of electrical equipment. Specifically, we described different 3D reconstruction techniques from different application scenarios of electrical equipment and elaborated on on-site requirements. Secondly, we emphasize the current application status of 3D reconstruction technology in the electrical industry and conduct a reasonable analysis of technical issues such as the combination of 3D reconstruction technology and electrical equipment monitoring. Finally, we discussed some key challenges and predicted future development trends.

A Review of Image 3D Reconstruction Technology and Its Application in Electrical Equipment Monitoring

This paper proposes a point cloud registration method for substations based on an improved SAC-IA algorithm. This method optimizes the SAC-IA algorithm by filtering the randomly selected point pairs to ensure that the triangles formed by the selected points in the model and scene point clouds have certain similarities. Furthermore, the registration error judgment of the SAC-IA algorithm has been improved. In addition to using the Euclidean distance between the registered model and scene point clouds as the judgment standard, this method also considers the SHOT difference and average curvature difference. Successful registration is only considered when all three standards are satisfied. The experimental research shows that the time performance of this method is twice as high as that of the traditional SAC-IA algorithm on average, and the recognition accuracy is improved in the recognition results.

A Point Cloud Registration Method for Substations Based on an Improved SAC-IA Algorithm

This paper presents a point cloud registration method for Antarctic power cabins based on an improved SAC-IA algorithm. To address the issues of measurement errors in structured light scanning and edge structure damage caused by traditional mean depth filtering, as well as inaccurate random point pair selection and long computation times in the SAC-IA algorithm, the following work was conducted: First, an improved depth filtering algorithm was designed to better filter out depth noise while preserving edge information. Second, ISS keypoint detection and cosine similarity were used to match the best feature pairs, combined with the RANSAC method to remove incorrect matches. Experimental results show that the improved algorithm significantly optimizes the number of key points and matching pairs, greatly saves computational resources, and enhances registration accuracy and robustness.

A Point Cloud Registration Method for Antarctic Power Cabins Based on an Improved SAC-IA Algorithm

3D laser scanning is widely used in modeling industrial scenes, involving crucial steps like point cloud (PC) data preprocessing and extracting modeling targets from scattered points. Extracting target PC data from larger scenes is more challenging than from smaller settings. To efficiently obtain high-quality scene data and modeling targets, we introduce an innovative approach with the adaptive density-based voxel grid filtering algorithm and a probability statistics histogram method during preprocessing. We also propose a novel method for automatic extraction of target PC data using the adjacent feature plane constraint (AFPC) clustering technique. Initially, we capture height characteristics of the target object's PC through experiential and statistical height attributes. Points corresponding to each height are then clustered based on the PC's density distribution using the density-based spatial clustering of applications with noise algorithm. The intersection of these results optimizes the position of the target object's extraction bounding box, achieving seamless automatic object extraction. Experimental results validate the effectiveness of our preprocessing methodology, with F1 scores of 97.7 % and 97.3 % for the 220 kV and 500 kV areas, respectively. Furthermore, our novel extraction method demonstrates the ability to autonomously and directly extract electrical equipment from substation PC data. 

Neighborhood constraint extraction for rapid modeling of point cloud scenes in large-scale power grid substations

In order to facilitate the digital transformation of conventional power grid, constructing the digital twin of power equipment is crucial. The primary task of the digital transformation is to build the 3D model of power equipment. However, existing methods cannot achieve digital twin modeling with high fidelity and efficiency. Therefore, a 3D reconstruction method for heterogenous data based on improved Neural Radiation Fields (NeRF) is proposed. By utilizing the infrared-visible image sequence, the spatial domain consistency of the heterogenous data is preserved by the image registration algorithm improved based on restricted matching region strategy (RMRS). Then, in order to focus on the characteristics of the equipment, a deep image matting network (DIM) is designed to eliminate the interference of complex background in the image. The pose of the camera is recovered from the visible images of the power equipment based on Structure From Motion (SFM). Finally, the NeRF is employed to complete the 3D reconstruction of the visible model and temperature field model of power equipment, enabling 3D fusion perception of the 2D heterogenous monitoring data. Experimental results show that this method can realize high-fidelity 3D reconstruction of power equipment within 30 s, which is superior to existing methods in terms of accuracy, modeling speed, automation degree, robustness and lightweight.

A 3D Reconstruction Method for Heterogeneous Data of Power Equipment Based on Improved Neural Radiation Fields

Reverse modeling is a kind of technology that transforms natural scenes into three-dimensional models. The models are generated manually by referring to the point cloud obtained by a laser scanner, which is time-consuming, laborious, and complicated. To address this problem, we propose an automatic modeling method for the point cloud data of substations. First, an algorithm is designed to automatically generate a component model library by referring to the standard structure of the substation equipment. Then, we improve the Euclidean clustering to segment disconnected point cloud data. Finally, corresponding points are found according to the SHOT feature descriptor, and each component is identified with Hough voting. After the location information for each element in the scene is obtained, the models can be transferred to the scene to replace the corresponding part in the point cloud, thus completing the process of automatic modeling. The experiment compares the results of improved Euclidean clustering and traditional Euclidean clustering. The clustering method in this paper has a significant improvement in execution efficiency. In addition, we also give the final modeling result of the method in this paper. Compared with the Delaunay triangulation and Poisson surface reconstruction methods, the model built by this method is more complete.

Study on the automatic modeling method of 3D information model for substations

3D point cloud semantic segmentation is one of the key technologies for fast 3D modeling of digital twins. To address the overfitting problem of the large-scale semantic segmentation model RandLA-Net, this paper proposes an improved RandLA-Net method based on Mix3D data augmentation. RandLA-Net is a high-volume, large-perception field model that can directly capture the contextual information of the entire 3D scene, while 3D datasets tend to be more expensive due to data sampling and labeling, often the number of scenes is small and the variance within the data is small, RandLA-Net can easily learn the overly strong contextual prior on the training set, and the model may show poor generalization ability when reasoning in realistic scenes. By introducing Mix3D to mix the two scenes to generate new training samples and implicitly place the object instances in the new contextual environment, the RandLA-Net model no longer relies solely on the scene context to infer semantic labels, but instead infer from the local structure, balancing the role of global context and local structure information in model inference and effectively reducing the overfitting of the training set context. The overfitting of the training set context is effectively reduced. Experimental results on several datasets show that our approach results in a 1.3% and 0.6% mIoU improvement of the RandLA-Net model on Semantic3D and S3DIS datasets.

Mix3D data augmentation enhanced RandLA-Net for large-scale point cloud semantic segmentation

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Junfeng Ding

Author Tools

Chat about Author

Papers

Study on the automatic modeling method of 3D information model for substations

Mix3D data augmentation enhanced RandLA-Net for large-scale point cloud semantic segmentation