CN116070523A - A simulation construction method of image samples for substation defect detection - Google Patents
A simulation construction method of image samples for substation defect detection Download PDFInfo
- Publication number
- CN116070523A CN116070523A CN202310141984.4A CN202310141984A CN116070523A CN 116070523 A CN116070523 A CN 116070523A CN 202310141984 A CN202310141984 A CN 202310141984A CN 116070523 A CN116070523 A CN 116070523A
- Authority
- CN
- China
- Prior art keywords
- fault
- substation
- simulation
- faults
- equipment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004088 simulation Methods 0.000 title claims abstract description 59
- 230000007547 defect Effects 0.000 title claims abstract description 24
- 238000010276 construction Methods 0.000 title claims abstract description 20
- 238000001514 detection method Methods 0.000 title claims abstract description 16
- 238000000034 method Methods 0.000 claims abstract description 33
- 230000003068 static effect Effects 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 9
- 238000011835 investigation Methods 0.000 claims abstract description 7
- 238000013480 data collection Methods 0.000 claims abstract description 4
- 238000002372 labelling Methods 0.000 claims abstract description 4
- 230000008439 repair process Effects 0.000 claims description 26
- 238000012423 maintenance Methods 0.000 claims description 14
- 238000005516 engineering process Methods 0.000 claims description 13
- 238000003384 imaging method Methods 0.000 claims description 9
- 230000008521 reorganization Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000004880 explosion Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000004321 preservation Methods 0.000 claims 1
- 230000000391 smoking effect Effects 0.000 claims 1
- 238000013461 design Methods 0.000 abstract description 6
- 230000000694 effects Effects 0.000 abstract description 5
- 238000012545 processing Methods 0.000 abstract 1
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000009413 insulation Methods 0.000 description 2
- 239000000779 smoke Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000013479 data entry Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/20—Packaging, e.g. boxes or containers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/04—Ageing analysis or optimisation against ageing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computer Graphics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Description
技术领域technical field
本发明涉及变电站图像样本仿真构建技术领域,尤其是涉及一种变电站缺陷检测图像样本仿真构建方法。The invention relates to the technical field of substation image sample simulation construction, in particular to a substation defect detection image sample simulation construction method.
背景技术Background technique
国民经济的发展与电力系统的稳定运行密切相关,变电站是电力系统的一个重要组成部分,确保变电站的正常运行对国民经济和人民的生活是非常重要的,电力设备或输电线路部件的松动和磨损将导致变电站稳定运行的破坏,因此有必要对变电站设备进行操作和维护,近年来,国家电网大力推进巡检机器人在变电站环境中的应用,依赖于使用深度神经网络训练得到的图像检测算法,巡检机器人已经能够实现缺陷检测、故障识别、仪表读数、闸刀和空气开关状态判断等功能,但是,图像训练样本的种类和数量影响着智能算法的准确性和泛化性。并且目前变电站环境下的缺陷样本图像数据集存在着严重不足,一方面该数据集的样本数量较少,无法涵盖各种电力设备可能出现的缺陷;另一方面,缺陷数据十分不平衡,绝缘子自爆、销钉缺失等缺陷相关样本的数量较多,而电缆断线散股、金具锈蚀等缺陷相关样本的数量较少;此外,一些设备所处位置较难拍摄,如固定在电线杆上的设备,难以从多角度拍摄缺陷图像。The development of the national economy is closely related to the stable operation of the power system. The substation is an important part of the power system. Ensuring the normal operation of the substation is very important to the national economy and people's lives. The looseness and wear of power equipment or transmission line components It will lead to the destruction of the stable operation of the substation, so it is necessary to operate and maintain the substation equipment. The inspection robot has been able to realize functions such as defect detection, fault identification, instrument reading, switch knife and air switch status judgment, but the type and quantity of image training samples affect the accuracy and generalization of intelligent algorithms. Moreover, there is a serious shortage of defect sample image datasets in the current substation environment. On the one hand, the number of samples in the dataset is small, which cannot cover the possible defects of various power equipment; on the other hand, the defect data is very unbalanced, and the insulators explode The number of samples related to defects such as missing pins and missing pins is relatively large, while the number of samples related to defects such as broken cables, loose strands, and corroded hardware is relatively small; in addition, some equipment locations are difficult to photograph, such as equipment fixed on utility poles, It is difficult to take images of defects from multiple angles.
目前,故障识别算法图像训练样本的获取途径有:(1)实地拍摄:使用无人机或机器人等图像拍摄设备在工业现场采集相关图像,将采集到的图像作为训练样本,并手动标注各图像中的故障类型和故障点,(2)虚拟仿真:设计仿真软件,模拟电力设备可能发生的各种故障仿真软件,并通过仿真软件中的传感器获得符合要求的可见光光学图像,(3)实物仿真:设计一个可以模拟各种故障发生时设备状态的实物,并手动采集图像,(4)智能算法:基于长短期记忆网络的仿真样本生成方法,基于生成式对抗网络的缺陷样本生成方法等等。At present, the ways to obtain image training samples for fault recognition algorithms are: (1) On-site shooting: use drones or robots to collect relevant images at industrial sites, use the collected images as training samples, and manually mark each image (2) virtual simulation: design simulation software, simulate various fault simulation software that may occur in power equipment, and obtain visible light optical images that meet the requirements through sensors in the simulation software, (3) physical simulation : Design a physical object that can simulate the state of equipment when various faults occur, and manually collect images, (4) Intelligent algorithm: simulation sample generation method based on long short-term memory network, defect sample generation method based on generative confrontation network, etc.
上述中的现有技术方案存在以下缺陷:(1)现场拍摄受时间、环境、场地等客观因素限制,无法覆盖各种可能因素影响下的设备故障场景,且消耗大量时间和人力资源;(2)物理仿真成本高,设计难度大。The above-mentioned existing technical solutions have the following defects: (1) On-site shooting is limited by objective factors such as time, environment, and venue, and cannot cover equipment failure scenarios under the influence of various possible factors, and consumes a lot of time and human resources; (2) ) The cost of physical simulation is high and the design is difficult.
发明内容Contents of the invention
本发明的目的是提供一种收集信息对变电站进行建模并模拟变电站故障的变电站缺陷检测图像样本仿真构建方法。The purpose of the present invention is to provide a simulation construction method of substation defect detection image samples for collecting information to model substations and simulating substation faults.
为实现上述目的,本发明提供了如下技术方案:To achieve the above object, the present invention provides the following technical solutions:
一种变电站缺陷检测图像样本仿真构建方法,其构建步骤如下:A simulation construction method for substation defect detection image samples, the construction steps are as follows:
S1:数据收集:对变电站环境进行实地考察,采集各设备的图形、尺寸、型号,确定变电站的原型,接着大量搜集每个设备的相关图片和图纸资料,并据此来对变电站和电气设备进行建模,使用三维建模软件来对虚拟变电站进行建模;S1: Data collection: Conduct on-the-spot investigations on the substation environment, collect the graphics, dimensions, and models of each equipment, determine the prototype of the substation, and then collect a large number of relevant pictures and drawings of each equipment, and conduct substation and electrical equipment based on this Modeling, using 3D modeling software to model the virtual substation;
S2:变电站建模:根据建模对象的大致形状选取合适的建模基本体,再根据实地考察和收集得到的设备图纸,将基本体转换为可编辑体,根据设备的尺寸和形状调节多边形的点、线、面,以得到完善的设备模型:S2: Substation modeling: select the appropriate modeling basic body according to the approximate shape of the modeling object, and then convert the basic body into an editable body according to the equipment drawings obtained from field investigation and collection, and adjust the polygonal shape according to the size and shape of the equipment Points, lines, and surfaces to get a complete device model:
S3:故障分析:对变电站设备常见故障数据进行分类和整理,从而获取故障分析后的数据,并根据故障分析后的数据设定相应的检修模式,并将检修模式的数据进行录入,从而获得故障数据库;S3: Fault analysis: Classify and organize the common fault data of substation equipment, so as to obtain the data after fault analysis, and set the corresponding maintenance mode according to the data after fault analysis, and input the data of the maintenance mode, so as to obtain the fault database;
S4:故障模拟:故障现象模拟模块负责根据故障数据库,模拟变电站环境中可能发生的各种故障,包括静态故障和动态故障,并将相应故障的检修方式通过文档或者视频链接的方式导入相应故障数据库,和故障数据提取出时一并提取,便于故障维修和模拟学习修理过程;S4: Fault simulation: The fault phenomenon simulation module is responsible for simulating various faults that may occur in the substation environment according to the fault database, including static faults and dynamic faults, and importing the repair methods of corresponding faults into the corresponding fault database through documents or video links , extracted together with the fault data, which is convenient for fault repair and simulation learning repair process;
S5:变电站运行仿真:基于虚拟现实技术建立变电站三维模拟环境,并设置相应的编辑程序,使用时,通过虚拟现实技术对各类典型设备故障进行实时模拟,模拟时对故障产生的情况进行分析,获取故障情况和故障修复信息,并利用虚拟现实技术进行在线展示,根据故障修复信息对故障进行模拟检修,并可以录入新的故障信息进行记录,方便对不同的故障进行检修和记录。S5: Substation operation simulation: establish a three-dimensional simulation environment for substations based on virtual reality technology, and set up corresponding editing programs. When in use, use virtual reality technology to simulate various typical equipment faults in real time, and analyze the faults during the simulation. Obtain fault conditions and fault repair information, and use virtual reality technology to display online, simulate fault repairs based on fault repair information, and can enter new fault information for recording, which is convenient for repairing and recording different faults.
S6:样本自动生成和标注:在虚拟变电站场景中根据摄像机的空间位置、方向和前向矢量对摄像机成像模型进行建模,在成像过程中,基于Render-To-Texture技术渲染生成高保真的图像文件,同时根据变电站三维仿真场景中成像设备的类型、故障类型、几何信息等,生成包围盒坐标、设备和故障类型的标注信息,以满足算法训练和语义标注信息的需要。S6: Automatic sample generation and labeling: In the virtual substation scene, the camera imaging model is modeled according to the camera's spatial position, direction, and forward vector. During the imaging process, high-fidelity images are generated based on Render-To-Texture technology. At the same time, according to the type of imaging equipment, fault type, geometric information, etc. in the substation 3D simulation scene, the bounding box coordinates, equipment and fault type annotation information are generated to meet the needs of algorithm training and semantic annotation information.
进一步的,所述S1中使用三维建模软件对虚拟变电站建模过程中采用标志性图标进行建模,并对标志性图标进行标注保存,便于后续提取标志性建筑进行模型的组建。Further, in the S1, three-dimensional modeling software is used to model the virtual substation with iconic icons, and the iconic icons are marked and saved, so as to facilitate subsequent extraction of iconic buildings for model building.
进一步的,所述S2中变电站建模对于几何结构较复杂的物体,使用分割重组的方式来对其建模,完成三个部分的模型制作后,通过拼接重组的方式使它们成为一个整体,基本建模出变电站设备的完整模型后,再使用贴图来完善模型的细节部分,在所有部件都建模后,通过拼接和重组来构建不同类型的设备,且拼接重组图标能够进行保存,形成常用图标,用来和标志性图标提取组合。Further, in the substation modeling in S2, for objects with complex geometric structures, the method of segmentation and reorganization is used to model them. After the three parts of the model are completed, they are integrated into a whole by means of splicing and reorganization, basically After modeling the complete model of the substation equipment, use textures to improve the details of the model. After all the parts are modeled, different types of equipment are constructed by splicing and reorganizing, and the splicing and reorganization icons can be saved to form common icons , used to combine with icon extraction.
进一步的,所述S3和S4中的故障包括静态故障和动态故障,且静态故障是指隔离开关没有完全闭合,绝缘线圈断裂的情况,动态故障是指变压器爆炸、电抗器冒烟的过程。Further, the faults in S3 and S4 include static faults and dynamic faults, and static faults refer to the situation that the isolation switch is not completely closed and the insulation coil is broken, and dynamic faults refer to the process of transformer explosion and reactor smoke.
进一步的,所述变电站运行仿真过程中的故障产生的情况分析后进行分类,将整体设置为实时保存模式,对不同故障类型进行记录,同时便于后续对新的故障进行及时记录分析。Further, after analyzing the situation of faults in the substation operation simulation process, they are classified, and the whole is set to a real-time storage mode to record different types of faults, and at the same time, it is convenient for subsequent timely recording and analysis of new faults.
进一步的,所述变电站运行仿真过程中的故障产生的情况分类记录后,将相应类别故障的维修方法进行调取,且故障的维修方法设置为实时记录模式,能够不断对不同的故障进行优化修理模式,便于模拟修理和进行修理知识学习。Further, after the classification and recording of faults in the operation simulation process of the substation, the maintenance method of the corresponding type of fault is called, and the fault maintenance method is set to the real-time recording mode, which can continuously optimize and repair different faults Mode, which is convenient for simulating repair and learning about repair knowledge.
综上所述,本发明的有益技术效果为:In summary, the beneficial technical effects of the present invention are:
1、该变电站缺陷检测图像样本仿真构建方法,使用三维建模软件来对虚拟变电站进行建模,首先,在建模前,我们对变电站环境进行实地考察,采集各设备的图形、尺寸、型号,确定变电站的原型,之后,大量搜集每个设备的相关图片和图纸资料,并据此来对变电站和电气设备进行建模,不需要完全通过拍摄的方式进行建模,降低整体的建模难度,达到了方便构建样本的效果;1. This substation defect detection image sample simulation construction method uses 3D modeling software to model the virtual substation. First, before modeling, we conduct on-the-spot inspections of the substation environment and collect the graphics, dimensions, and models of each equipment. Determine the prototype of the substation, and then collect a large number of relevant pictures and drawings of each equipment, and model the substation and electrical equipment based on this. It does not need to be modeled entirely by shooting, reducing the overall difficulty of modeling. Achieved the effect of conveniently constructing samples;
2、该变电站缺陷检测图像样本仿真构建方法,采用虚拟现实技术实现故障现象模拟模块的开发,首先,大量了解变电站环境中存在的故障情况,接着,对我们分类的静态以及动态故障进行针对性模拟,并将相应的解决方法进行同时提取,方便进行解决和学习,达到了针对性模拟的效果。2. The simulation construction method of the substation defect detection image sample uses virtual reality technology to realize the development of the fault phenomenon simulation module. First, a large amount of fault conditions existing in the substation environment are understood, and then, the static and dynamic faults classified by us are targeted for simulation. , and extract the corresponding solutions at the same time, which is convenient for solving and learning, and achieves the effect of targeted simulation.
3、该变电站缺陷检测图像样本仿真构建方法,生成的一个包含故障设备、故障现象等故障相关信息的单独渲染图像文件来对图像中的故障位置或故障类型等信息进行标注,借此实现对图像训练样本标注故障点和故障类型的自动获取,达到了便于模拟训练的效果。3. The substation defect detection image sample simulation construction method generates a separate rendering image file containing fault-related information such as faulty equipment and fault phenomena to mark the fault location or fault type in the image, thereby realizing the image The automatic acquisition of training samples to mark fault points and fault types achieves the effect of facilitating simulation training.
附图说明Description of drawings
图1为本发明工作流程示意图。Figure 1 is a schematic diagram of the workflow of the present invention.
具体实施方式Detailed ways
以下结合附图对本发明方法作进一步详细说明。The method of the present invention will be described in further detail below in conjunction with the accompanying drawings.
参照附图1,一种变电站缺陷检测图像样本仿真构建方法,其特征在于,其构建步骤如下:With reference to accompanying drawing 1, a kind of substation defect detection image sample simulation construction method is characterized in that, its construction steps are as follows:
S1:数据收集:对变电站环境进行实地考察,采集各设备的图形、尺寸、型号,确定变电站的原型,接着大量搜集每个设备的相关图片和图纸资料,并据此来对变电站和电气设备进行建模,使用三维建模软件来对虚拟变电站进行建模,使用三维建模软件对虚拟变电站建模过程中采用标志性图标进行建模,并对标志性图标进行标注保存,便于后续提取标志性建筑进行模型的组建,三维建模软件是通过二维的平面照片组合形成类似于拍摄场地的软件,是现有且公知的技术常识,本设计主要是针对变电站故障的模拟,建模软件的选用和使用不为本设计重点,所以不多做描述;S1: Data collection: Conduct on-the-spot investigations on the substation environment, collect the graphics, dimensions, and models of each equipment, determine the prototype of the substation, and then collect a large number of relevant pictures and drawings of each equipment, and conduct substation and electrical equipment based on this Modeling, use 3D modeling software to model the virtual substation, use 3D modeling software to model the virtual substation with iconic icons in the modeling process, and mark and save the iconic icons to facilitate subsequent extraction of iconic The construction of the model of the building, the 3D modeling software is a combination of two-dimensional plane photos to form software similar to the shooting site, which is an existing and well-known technical common sense. This design is mainly for the simulation of substation faults, and the selection of modeling software And use is not the focus of this design, so I won't describe it more;
S2:变电站建模:根据建模对象的大致形状选取合适的建模基本体,再根据实地考察和收集得到的设备图纸,将基本体转换为可编辑体,根据设备的尺寸和形状调节多边形的点、线、面,以得到完善的设备模型,变电站建模对于几何结构较复杂的物体,使用分割重组的方式来对其建模,完成三个部分的模型制作后,通过拼接重组的方式使它们成为一个整体,基本建模出变电站设备的完整模型后,再使用贴图来完善模型的细节部分,在所有部件都建模后,通过拼接和重组来构建不同类型的设备,且拼接重组图标能够进行保存,形成常用图标,用来和标志性图标提取组合,常用图标为变电站中存在的一般设备,即大多变电站共有设备,通过相同的图标进行表示并命名,方便后续提取,标志性图标是指和一般设备不同的特殊设备,根据变电站的工作类型可能会存在较大型和或者特殊型的设备,需要特殊建模,并设置不同的数据,以便于更加适配于变电站内部情况,保证模拟的精准性;S2: Substation modeling: select the appropriate modeling basic body according to the approximate shape of the modeling object, and then convert the basic body into an editable body according to the equipment drawings obtained from field investigation and collection, and adjust the polygonal shape according to the size and shape of the equipment Points, lines, and surfaces to obtain a complete equipment model. Substation modeling For objects with complex geometric structures, use the method of segmentation and reorganization to model them. They become a whole. After basically modeling the complete model of the substation equipment, the textures are used to improve the details of the model. After all the parts are modeled, different types of equipment are constructed by splicing and reorganizing, and the splicing and reorganization icons can Save and form commonly used icons, which are used to extract and combine with iconic icons. Commonly used icons are general equipment in substations, that is, common equipment in most substations. They are represented and named by the same icon to facilitate subsequent extraction. Iconic icons refer to For special equipment that is different from general equipment, there may be larger or special equipment depending on the type of work in the substation, which requires special modeling and different data settings to better adapt to the internal conditions of the substation and ensure the accuracy of the simulation sex;
S3:故障分析:对变电站设备常见故障数据进行分类和整理,从而获取故障分析后的数据,并根据故障分析后的数据设定相应的检修模式,并将检修模式的数据进行录入,从而获得故障数据库,故障数据库可以进行数据的录入和提取,从而根据变电站模拟情况出现的可能,对故障产生的可能情况进行提取,方便根据实际情况进行维修;S3: Fault analysis: Classify and organize the common fault data of substation equipment, so as to obtain the data after fault analysis, and set the corresponding maintenance mode according to the data after fault analysis, and input the data of the maintenance mode, so as to obtain the fault The database and the fault database can be used for data entry and extraction, so that the possible faults can be extracted according to the possibility of substation simulation, so as to facilitate maintenance according to the actual situation;
S4:故障模拟:故障现象模拟模块负责根据故障数据库,模拟变电站环境中可能发生的各种故障,包括静态故障和动态故障,并将相应故障的检修方式通过文档或者视频链接的方式导入相应故障数据库,和故障数据提取出时一并提取,便于故障维修和模拟学习修理过程,故障包括静态故障和动态故障,且静态故障是指隔离开关没有完全闭合,绝缘线圈断裂的情况,动态故障是指变压器爆炸、电抗器冒烟的过程,静态故障和动态故障设置在不同的数据库内,当变电站发生故障时,首先对故障类型进行检索,降低检索的范围,从而增加检索的速度;S4: Fault simulation: The fault phenomenon simulation module is responsible for simulating various faults that may occur in the substation environment according to the fault database, including static faults and dynamic faults, and importing the repair methods of corresponding faults into the corresponding fault database through documents or video links , which is extracted together with the fault data, which is convenient for fault maintenance and simulated learning and repair process. Faults include static faults and dynamic faults, and static faults refer to the situation that the isolating switch is not completely closed and the insulation coil is broken. Dynamic faults refer to the transformer In the process of explosion and reactor smoke, static faults and dynamic faults are set in different databases. When a fault occurs in a substation, the fault type is first searched to reduce the range of retrieval and increase the speed of retrieval;
S5:变电站运行仿真:基于虚拟现实技术建立变电站三维模拟环境,并设置相应的编辑程序,使用时,通过虚拟现实技术对各类典型设备故障进行实时模拟,模拟时对故障产生的情况进行分析,获取故障情况和故障修复信息,并利用虚拟现实技术进行在线展示,根据故障修复信息对故障进行模拟检修,并可以录入新的故障信息进行记录,方便对不同的故障进行检修和记录,所述变电站运行仿真过程中的故障产生的情况分析后进行分类,将整体设置为实时保存模式,对不同故障类型进行记录,同时便于后续对新的故障进行及时记录分析,所述变电站运行仿真过程中的故障产生的情况分类记录后,将相应类别故障的维修方法进行调取,且故障的维修方法设置为实时记录模式,能够不断对不同的故障进行优化修理模式,便于模拟修理和进行修理知识学习。S5: Substation operation simulation: establish a three-dimensional simulation environment for substations based on virtual reality technology, and set up corresponding editing programs. When in use, use virtual reality technology to simulate various typical equipment faults in real time, and analyze the faults during the simulation. Obtain fault conditions and fault repair information, and use virtual reality technology to display online, simulate fault repairs based on fault repair information, and record new fault information, which is convenient for repairing and recording different faults. The substation After the situation analysis of the faults in the operation simulation process, it is classified, the whole is set to the real-time saving mode, and different types of faults are recorded, and at the same time, it is convenient for subsequent timely recording and analysis of new faults. The faults in the operation simulation process of the substation After the generated situation is classified and recorded, the maintenance method of the corresponding type of failure is called, and the maintenance method of the failure is set to the real-time recording mode, which can continuously optimize the repair mode for different failures, which is convenient for simulated repair and repair knowledge learning.
S6:样本自动生成和标注:在虚拟变电站场景中根据摄像机的空间位置、方向和前向矢量对摄像机成像模型进行建模,在成像过程中,基于Render-To-Texture技术渲染生成高保真的图像文件,同时根据变电站三维仿真场景中成像设备的类型、故障类型、几何信息等,生成包围盒坐标、设备和故障类型的标注信息,以满足算法训练和语义标注信息的需要;S6: Automatic sample generation and labeling: In the virtual substation scene, the camera imaging model is modeled according to the camera's spatial position, direction, and forward vector. During the imaging process, high-fidelity images are generated based on Render-To-Texture technology. At the same time, according to the type of imaging equipment, fault type, geometric information, etc. in the substation 3D simulation scene, the bounding box coordinates, equipment and fault type annotation information are generated to meet the needs of algorithm training and semantic annotation information;
所述变电站运行仿真过程中的故障产生的情况分析后进行分类,将整体设置为实时保存模式,对不同故障类型进行记录,同时便于后续对新的故障进行及时记录分析。The faults in the substation operation simulation process are analyzed and classified, and the whole is set to a real-time storage mode to record different types of faults, and at the same time, it is convenient for subsequent timely recording and analysis of new faults.
本具体实施方式的实施例均为本发明的较佳实施例,并非依此限制本发明的保护范围,故:凡依本发明的结构、形状、原理所做的等效变化,均应涵盖于本发明的保护范围之内。The embodiments of this specific implementation mode are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention, so: all equivalent changes made according to the structure, shape and principle of the present invention should be covered by within the protection scope of the present invention.
Claims (6)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310141984.4A CN116070523A (en) | 2023-02-21 | 2023-02-21 | A simulation construction method of image samples for substation defect detection |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310141984.4A CN116070523A (en) | 2023-02-21 | 2023-02-21 | A simulation construction method of image samples for substation defect detection |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116070523A true CN116070523A (en) | 2023-05-05 |
Family
ID=86180105
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310141984.4A Pending CN116070523A (en) | 2023-02-21 | 2023-02-21 | A simulation construction method of image samples for substation defect detection |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116070523A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117150414A (en) * | 2023-10-17 | 2023-12-01 | 广东迅扬科技股份有限公司 | Fault diagnosis method |
CN118397195A (en) * | 2024-06-24 | 2024-07-26 | 深圳供电局有限公司 | Power distribution abnormality alarm method, device, electronic device and computer readable medium |
CN119413840A (en) * | 2025-01-06 | 2025-02-11 | 内蒙古电力(集团)有限责任公司内蒙古电力科学研究院分公司 | A method and system for analyzing the causes of current-induced thermal defects in metal fittings in regional structures and for closed-loop processing |
-
2023
- 2023-02-21 CN CN202310141984.4A patent/CN116070523A/en active Pending
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117150414A (en) * | 2023-10-17 | 2023-12-01 | 广东迅扬科技股份有限公司 | Fault diagnosis method |
CN117150414B (en) * | 2023-10-17 | 2024-04-12 | 广东迅扬科技股份有限公司 | Fault diagnosis method |
CN118397195A (en) * | 2024-06-24 | 2024-07-26 | 深圳供电局有限公司 | Power distribution abnormality alarm method, device, electronic device and computer readable medium |
CN119413840A (en) * | 2025-01-06 | 2025-02-11 | 内蒙古电力(集团)有限责任公司内蒙古电力科学研究院分公司 | A method and system for analyzing the causes of current-induced thermal defects in metal fittings in regional structures and for closed-loop processing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112633535B (en) | Intelligent inspection method and system for photovoltaic power station based on unmanned aerial vehicle image | |
CN116070523A (en) | A simulation construction method of image samples for substation defect detection | |
CN110133443B (en) | Method, system and device for detection of power transmission line components based on parallel vision | |
CN111384776B (en) | VR-based transformer substation three-dimensional panoramic state monitoring method and system | |
CN117726958B (en) | Target detection and intelligent identification method of hidden dangers in UAV inspection images of distribution lines | |
CN109886947A (en) | High-voltage wire defect detection method based on region convolutional neural network | |
CN111044149A (en) | Method and device for detecting temperature abnormal point of voltage transformer and readable storage medium | |
CN110322564A (en) | A kind of 3 D model construction method of the substation operation environment suitable for VR/AR | |
CN117351521B (en) | Digital twinning-based power transmission line bird detection method, system, medium and equipment | |
CN111429578B (en) | Three-dimensional model generation method and three-dimensional virtual overhaul system for thermal power plant unit | |
CN114821852B (en) | Power grid defect depth identification inspection robot control system based on feature pyramid | |
CN109146880A (en) | A kind of electric device maintenance method based on deep learning | |
You | PCB defect detection based on generative adversarial network | |
CN111696209A (en) | Thermal power generating unit three-dimensional overhaul training framework, method and system based on reverse engineering | |
Menezes et al. | A survey on extended reality, digital twins, and metaverse applications in power systems | |
CN117151699A (en) | An operation and maintenance inspection method and system based on power scenario model | |
Liu et al. | EMB-YOLO: Dataset, method and benchmark for electric meter box defect detection | |
CN119338984A (en) | A method for building a substation metaverse scene using a virtual engine and its data system | |
CN118864723A (en) | A three-dimensional video fusion method and system based on digital twin technology | |
CN117034384A (en) | Digital three-dimensional simulation method for high-voltage equipment of power grid substation | |
CN116596880A (en) | PCB defect detection system and method based on NVIDIA Jetson TX2 | |
CN115689206A (en) | Intelligent monitoring method for transformer substation infrastructure progress based on deep learning | |
Wang et al. | The transmission line foreign body detection algorithm based on weighted spatial attention | |
Hu et al. | A detecting algorithm for occlusion on the surface of photovoltaic modules based on improved YOLOv5 | |
CN114170515A (en) | Power distribution network equipment abnormity type detection method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |