CN-121982255-A - Method, device, medium and program product for determining distance between substation equipment

CN121982255ACN 121982255 ACN121982255 ACN 121982255ACN-121982255-A

Abstract

The invention discloses a method, a device, a medium and a program product for determining the distance between substation equipment. Relates to the field of power systems. The method comprises the steps of obtaining point cloud data of a transformer substation, preprocessing the point cloud data to obtain target point cloud data, inputting the target point cloud data into a target modeling system to obtain a Gaussian three-dimensional model, processing the Gaussian three-dimensional model by a target gridding strategy to obtain a processed Gaussian three-dimensional model, and constructing a target index structure based on the processed Gaussian three-dimensional model, wherein the type of the target index structure comprises an index structure of a K-dimensional tree of the processed Gaussian three-dimensional model, and determining the shortest space distance between any two devices in the transformer substation based on the Gaussian three-dimensional model and the target index structure. The method solves the technical problem that the measurement accuracy of the shortest space distance between devices based on the transformer substation 3D Gaussian object is low.

Inventors

ZHOU KAI
GONG QIYANG
WANG ZHAOFEI
SHI BINGHENG
JIA DONGMING
YANG GUANQING
WANG HUAWEI
Li duojiao
CAI QING
MA FENG
LIU JUNJIE
YI SHUWEI
DONG XIANG
Xia boya
XU LINGFEI
LIU YUWU

Assignees

国网北京市电力公司

Dates

Publication Date: 20260505
Application Date: 20260127

Claims (10)

1. A method for determining a distance between substation devices, comprising: acquiring point cloud data of a transformer substation, and preprocessing the point cloud data to obtain target point cloud data, wherein a plurality of devices are deployed in the transformer substation; inputting the target point cloud data into a target modeling system to obtain a Gaussian three-dimensional model, wherein the target modeling system is used for carrying out 3D Gaussian splatter modeling on the target point cloud data; Processing the Gaussian three-dimensional model by adopting a target gridding strategy to obtain a processed Gaussian three-dimensional model, wherein the target gridding strategy is used for adjusting the size and distribution of voxels according to the density distribution characteristics of the equipment; Constructing a target index structure based on the processed Gaussian three-dimensional model, wherein the type of the target index structure comprises an index structure of a K-dimensional tree of the processed Gaussian three-dimensional model, and K is a positive integer; And determining the shortest space distance between any two devices in the transformer substation based on the Gaussian three-dimensional model and the target index structure.
2. The method for determining the distance according to claim 1, wherein the processed Gaussian three-dimensional model comprises equipment single point clouds of each equipment in the transformer substation, the equipment single point clouds comprise point cloud data processed through 3D Gaussian splatter modeling and the target meshing strategy, and the method for constructing the target index structure based on the processed Gaussian three-dimensional model comprises the following steps: analyzing the data quantity of the single point clouds of any two devices to determine an analysis result; under the condition that the analysis result indicates that the data quantity difference degree between the single point clouds of any two devices exceeds a preset degree threshold, merging the single point clouds of the two devices, and constructing an index structure of a K-dimensional tree based on the merged single point clouds of the devices to obtain a first index structure; Under the condition that the analysis result indicates that the data quantity difference degree between the device single point clouds of any two pieces of equipment does not exceed a preset degree threshold, respectively constructing index structures of K-dimensional trees for the device single point clouds of the two pieces of equipment to obtain a second index structure; The target index structure is determined based on the first index structure and the second index structure.
3. The pitch determination method according to claim 1, wherein analyzing the data amount of the device single point clouds of any two of the devices to determine the analysis result includes: Calculating information entropy between data volumes of single point clouds of any two pieces of equipment to obtain point cloud information entropy between every two pieces of equipment; under the condition that the point cloud information entropy of any two pieces of equipment is smaller than a preset threshold, determining that the degree of data quantity difference between the single point clouds of the equipment indicated by the analysis results exceeds the preset degree threshold; And under the condition that the point cloud information entropy of any two pieces of equipment is not smaller than a preset threshold, determining that the degree of data quantity difference between the single point clouds of the equipment indicated by the analysis results does not exceed the preset degree threshold.
4. The method of claim 2, wherein determining a shortest spatial distance between any two devices within the substation based on the gaussian three-dimensional model and the target index structure comprises: For any two pieces of equipment, calculating the distance between each pair of point clouds of the single equipment of the two pieces of equipment by adopting a nearest neighbor searching strategy based on a Gaussian three-dimensional model and the target index structure to obtain a distance set of the two pieces of equipment; And determining the shortest spatial distance between the two devices based on the smallest distance in the distance set of the two devices.
5. The pitch determination method according to claim 1, wherein processing the gaussian three-dimensional model using a target meshing strategy to obtain a processed gaussian three-dimensional model comprises: Determining the voxel grid size of each region based on the point cloud density distribution of different regions in the Gaussian three-dimensional model; And dividing the Gaussian three-dimensional model based on the voxel grid size of each region to obtain the processed Gaussian three-dimensional model.
6. The pitch determination method of claim 1, further comprising, prior to constructing a target index structure based on the processed gaussian three-dimensional model: dividing the processed Gaussian three-dimensional model to obtain initial point cloud clusters of each equipment type; And determining a plurality of single-equipment point clouds based on the initial point cloud clusters of each equipment type, wherein each single-equipment point cloud comprises the point cloud of one equipment in the transformer substation.
7. The distance determining method according to claim 1, wherein preprocessing the point cloud data to obtain target point cloud data includes: Filtering the point cloud data by adopting a target filtering strategy to obtain filtered point cloud data, wherein the target filtering strategy comprises at least one of statistical filtering and radius filtering; Filling the missing values in the filtered point cloud data by adopting a target filling strategy to obtain filled point cloud data, wherein the target filling strategy comprises at least one of plane fitting and curved surface difference; performing downsampling operation on the area with the point cloud density larger than a preset density threshold in the filled point cloud data to obtain the operated point cloud data; And determining the target point cloud data based on the operated point cloud data.
8. A pitch determination apparatus for substation equipment, characterized by comprising: the first processing unit is used for acquiring point cloud data of a transformer substation, preprocessing the point cloud data to obtain target point cloud data, and arranging a plurality of devices in the transformer substation; The second processing unit is used for inputting the target point cloud data into a target modeling system to obtain a Gaussian three-dimensional model, wherein the target modeling system is used for carrying out 3D Gaussian splatter modeling on the target point cloud data; the third processing unit is used for processing the Gaussian three-dimensional model by adopting a target gridding strategy to obtain a processed Gaussian three-dimensional model, wherein the target gridding strategy is used for adjusting the size and distribution of voxels according to the density distribution characteristics of the equipment; the construction unit is used for constructing a target index structure based on the processed Gaussian three-dimensional model, wherein the type of the target index structure comprises an index structure of a K-dimensional tree of the processed Gaussian three-dimensional model, and K is a positive integer; and the determining unit is used for determining the shortest space distance between any two devices in the transformer substation based on the Gaussian three-dimensional model and the target index structure.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises a stored executable program, wherein the computer-readable storage medium is controlled to perform the pitch determination method of the substation equipment according to any one of claims 1 to 7 when the executable program runs.
10. A computer program product comprising computer instructions which, when executed by a processor, carry out the steps of the pitch determination method of a substation device according to any one of claims 1 to 7.

Description

Method, device, medium and program product for determining distance between substation equipment Technical Field The invention relates to the field of power systems, in particular to a method, a device, a medium and a program product for determining the distance between substation equipment. Background With the continuous development of the power system in the intelligent and digital directions, the transformer substation is used as an important hub of the power grid, and the running safety and maintenance efficiency of equipment of the transformer substation have a critical influence on the stability of the whole power system. Traditional modes such as manual inspection and two-dimensional drawing inspection are difficult to meet the increasingly complex structure and urgent operation and maintenance requirements of modern substations. In a substation 3DGS scene, accurate measurement of the shortest space distance between devices is the core of various key applications such as electrical safety evaluation, assembly check, span detection and the like. The bus and the bus must keep a certain phase-to-phase insulation distance, and the design specification must be satisfied between the insulator and the metal component, otherwise, corona discharge and partial discharge are extremely easy to cause, even flashover breakdown is caused, and the operation safety of a power grid is seriously threatened. In addition, substation equipment layout is generally complex in space, multiple layers of crossing, horizontal and vertical pipe gallery staggering and interactive reflection of various metal and insulating materials exist, and difficulty in distance measurement among models is greatly increased. From a data scale perspective, a complete 3DGS acquisition reconstruction typically generates tens of millions of data sets. If the traditional O (n 2) violent search is adopted, the calculated amount is increased in a square level, real-time performance cannot be guaranteed, if a simple geometric bounding volume (such as a convex hull and an OBB (directed bounding box)) is used for approximate calculation, although detail structures are easy to ignore, a large error exists in a measurement result, for example, a convex hull-based calculation method simplifies the shortest distance calculation by constructing a convex hull of a point cloud. A convex hull is the smallest convex polyhedron that contains all points, representing the outer boundary of the point cloud. The shortest distance between the point clouds can be approximately estimated by calculating the shortest distance between the two point cloud convex hulls, but for point clouds with complex shapes or concave shapes, the convex hulls may not accurately describe their boundaries, resulting in inaccurate distance calculation. The computational complexity of constructing convex hulls is high, especially in high-dimensional space. The directed bounding box (OBB) is a smallest volume rectangular box that closely encloses a point cloud, the direction of which can be adjusted according to the main direction of the point cloud. By calculating the shortest distance between the OBBs of two point clouds, the shortest distance between the point clouds can be quickly estimated. The method is suitable for scenes with regular shape and definite direction of the point cloud. For point clouds with irregular shapes or inconsistent directions, the OBB may not accurately enclose the point cloud, resulting in inaccurate distance calculation. The OBB construction has higher calculation complexity and needs to perform operations such as principal component analysis. In the transformer substation, if the distance deviation of micro components such as bus bar joints, small sensors, insulator petals and the like is only in millimeter level, the equipment installation precision and the operation safety can be affected. In view of the above problems, no effective solution has been proposed at present. Disclosure of Invention The embodiment of the invention provides a distance determining method, device, medium and program product of substation equipment, which at least solve the technical problem of low measurement accuracy of the shortest space distance between the equipment based on a substation 3D Gaussian object in the related technology. According to one aspect of the embodiment of the invention, a distance determining method of substation equipment is provided, which comprises the steps of obtaining point cloud data of a substation, preprocessing the point cloud data to obtain target point cloud data, inputting the target point cloud data into a target modeling system to obtain a Gaussian three-dimensional model, wherein the target modeling system is used for carrying out 3D Gaussian splash modeling on the target point cloud data, processing the Gaussian three-dimensional model by adopting a target gridding strategy to obtain a processed Gaussian three-dimensional model, wherein the t