CN111144325A - Fault identification and positioning method, device and equipment for power equipment of transformer substation - Google Patents
Fault identification and positioning method, device and equipment for power equipment of transformer substation Download PDFInfo
- Publication number
- CN111144325A CN111144325A CN201911384876.XA CN201911384876A CN111144325A CN 111144325 A CN111144325 A CN 111144325A CN 201911384876 A CN201911384876 A CN 201911384876A CN 111144325 A CN111144325 A CN 111144325A
- Authority
- CN
- China
- Prior art keywords
- image
- point cloud
- power equipment
- fault
- data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 92
- 238000000605 extraction Methods 0.000 claims description 33
- 238000001914 filtration Methods 0.000 claims description 26
- 230000008569 process Effects 0.000 claims description 25
- 238000004458 analytical method Methods 0.000 claims description 23
- 238000012545 processing Methods 0.000 claims description 23
- 238000007781 pre-processing Methods 0.000 claims description 20
- 238000013527 convolutional neural network Methods 0.000 claims description 19
- 238000010276 construction Methods 0.000 claims description 13
- 239000000284 extract Substances 0.000 claims description 13
- 238000012952 Resampling Methods 0.000 claims description 11
- 238000012216 screening Methods 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000013135 deep learning Methods 0.000 claims description 9
- 238000009499 grossing Methods 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 239000000463 material Substances 0.000 abstract description 11
- 238000007689 inspection Methods 0.000 abstract description 10
- 230000006870 function Effects 0.000 description 9
- 238000011176 pooling Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 239000003990 capacitor Substances 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000009440 infrastructure construction Methods 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 229910052573 porcelain Inorganic materials 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention relates to a fault identification and positioning method, a fault identification and positioning device and equipment of transformer substation power equipment. The method can identify the position of the power equipment of the transformer substation, has high identification efficiency, does not need to invest a large amount of manpower and material resources, and greatly improves the accuracy and efficiency of identifying the fault of the power equipment by eliminating the interference of disordered images and irrelevant factors on the fault identification. The technical problems that a large amount of manpower and material resources are needed to be input and the working efficiency is low in the traditional method for detecting the faults in the routing inspection of the transformer substation are solved.
Description
Technical Field
The invention relates to the technical field of power equipment fault identification, in particular to a fault identification and positioning method, device and equipment for power equipment of a transformer substation.
Background
The high-speed development of the power industry, a large number of transformer substations are generated, the transformer substations are complex projects from inexistence to existence and from stability to sustainable use, and the establishment of the transformer substations puts high requirements on infrastructure construction. The power generation equipment required by the transformer substation is not only large in quantity, but also precise and complex, which means that the workload of equipment line laying is huge.
In the traditional construction process of a transformer substation, a large amount of drawings, data, reports and the like can be generated, management is inconvenient, a plurality of specialties and departments are involved, once a plurality of problems are encountered in construction, a large amount of on-site investigation and investigation needs to be carried out by all construction units and related departments, and the positions and the problems of faults can be found through multiple research and negotiation, the problems are solved, the process is always painstakingly conducted, the efficiency is very low, and the quality of the final solution is not high. Therefore, in the later maintenance of the transformer substation, the transformer work area of the transformer substation is a typical high-risk work area, which is the central importance of the power transmission field, and major accidents are easy to happen without paying attention.
With the development of socioeconomic in China, the demand for electric energy is increasing day by day. The operation inspection and the state monitoring of the power equipment in the transformer substation are used as emerging industries developed in recent years, and huge growth potential and development space are presented.
Along with the progress of science and technology and the promotion of digital city construction, the work of manual inspection is gradually replaced by automatic robots, the times of manual inspection are greatly reduced, but the robots cannot completely replace the work of people. Aiming at large and complex equipment of various electric equipment (main transformer, circuit breaker, capacitor and the like) in a transformer substation, the traditional inspection fault of the transformer substation is carried out by adopting a model manufactured by collecting data by a total station, the whole model is more difficult to establish, a large amount of resources such as manpower, material resources, financial resources and the like still need to be input, and the working efficiency of the mode is low.
Therefore, in the inspection process of the substation, how to improve and identify the fault position of the substation becomes an important technical problem to be solved urgently by technical personnel in the field.
Disclosure of Invention
The embodiment of the invention provides a fault identification and positioning method, a fault identification and positioning device and a fault identification and positioning device for power equipment of a transformer substation, which are used for solving the technical problems that a large amount of manpower and material resources are required to be input and the working efficiency is low in the traditional method for detecting faults in the transformer substation.
In order to achieve the above object, the embodiments of the present invention provide the following technical solutions:
a fault identification and positioning method for substation power equipment comprises the following steps:
s1, data acquisition: acquiring three-dimensional point cloud data of all power equipment images in a transformer substation;
s2, data preprocessing: carrying out filtering pretreatment on the three-dimensional point cloud data to obtain point cloud data;
s3, constructing a model image: processing the point cloud data through resampling, data splicing and matching, and constructing the processed data into a three-dimensional model image;
s4, extracting image features: carrying out feature extraction on the model image to obtain image features;
s5, image classification: classifying the image features by adopting a convolutional neural network to obtain image feature classifications;
s6, constructing a fault identification model: training the image feature classification and the image features by adopting deep learning to obtain a fault recognition model;
s7, fault identification and analysis: and acquiring an image to be detected of one of the power equipment of the transformer substation, inputting the image to be detected into the fault identification model for identification and analysis, and obtaining the specific position of the power equipment without fault or fault.
Preferably, the three-dimensional point cloud data and the image to be detected are obtained by scanning power equipment through a three-dimensional laser scanner.
Preferably, in step S2, an octree segmentation algorithm is used to perform denoising and smoothing filtering on the three-dimensional point cloud data to obtain the point cloud data.
Preferably, in the step S3, the processing of the point cloud data includes:
simplifying and screening the point cloud data by adopting the resampled point cloud to obtain messy point cloud data;
performing data splicing on the messy point cloud data through the data splicing and a target splicing and homonymous point mixed splicing method matched with the data splicing method to obtain the spliced point cloud data;
and unifying the spliced point cloud data to the same coordinate system by adopting point cloud registration to form the three-dimensional model image.
Preferably, in step S4, a Gist feature extraction method is adopted to extract features of the naturalness, openness, and expansion of the model image, so as to obtain image features; and in the process of extracting the image characteristics, a Gabor filtering mode is adopted to extract different textures of the image from the direction and the size of the model image.
Preferably, in step S7, the image of the fault identification model includes a visible light image, if the power device of the image to be detected has a fault, the image to be detected is input into the fault identification model, and the fault identification model is displayed on the visible light image after the image features are classified and analyzed, so as to obtain an accurate fault position of the image to be detected.
The invention also provides a fault identification and positioning device of the power equipment of the transformer substation, which comprises the following components:
the data acquisition unit is used for acquiring three-dimensional point cloud data of all power equipment images in the transformer substation;
the preprocessing unit is used for carrying out filtering preprocessing on the three-dimensional point cloud data to obtain point cloud data;
a model image constructing unit for processing the point cloud data through resampling, data splicing and matching and constructing the processed data into a three-dimensional model image;
the characteristic extraction unit is used for extracting the characteristics of the model image to obtain image characteristics;
the image classification unit is used for classifying the image features by adopting a convolutional neural network to obtain image feature classifications;
a fault recognition model building unit for training the image feature classification and the image features by adopting deep learning to obtain a fault recognition model;
and the fault identification and analysis unit is used for acquiring an image to be detected of one of the electric power equipment of the transformer substation, and the image to be detected is input into the fault identification model for identification and analysis to obtain the specific position of the electric power equipment without fault or fault.
Preferably, the preprocessing unit performs denoising and smoothing filtering processing on the three-dimensional point cloud data by adopting an octree method segmentation algorithm to obtain the point cloud data;
the feature extraction unit extracts features of the naturalness, the openness and the expansion of the model image by adopting a Gist feature extraction mode to obtain image features; and in the process of extracting the image characteristics, a Gabor filtering mode is adopted to extract different textures of the image from the direction and the size of the model image.
Preferably, the model image building unit comprises a screening unit, a data splicing unit and a three-dimensional modeling unit;
the screening unit is used for simplifying and screening the point cloud data by adopting the resampled point cloud to obtain messy point cloud data;
the data splicing unit is used for performing data splicing on the messy point cloud data through the data splicing, target splicing matched with the data splicing and a homonymous point mixed splicing method to obtain the spliced point cloud data;
and the three-dimensional modeling unit is used for unifying the spliced point cloud data into the same coordinate system by adopting point cloud registration to form a three-dimensional model image.
The invention also provides a device comprising a processor and a memory;
the memory is used for storing program codes and transmitting the program codes to the processor;
and the processor is used for executing the fault identification and positioning method of the substation power equipment according to the instructions in the program codes.
According to the technical scheme, the embodiment of the invention has the following advantages:
1. the fault identification and positioning method of the power equipment of the transformer substation comprises the steps of data acquisition, data preprocessing, model image construction, image feature extraction and image classification, wherein a fault identification model is constructed, an image to be detected of the power equipment of the transformer substation is input into the fault identification model, the fault identification model identifies and analyzes whether the power equipment in the image to be detected is in fault or not, and if the fault occurs, the fault identification model identifies and analyzes the position of the power equipment of the transformer substation in fault. The fault identification and positioning method for the power equipment of the transformer substation can eliminate the interference of disordered images and irrelevant factors on fault identification, and greatly improves the accuracy and efficiency of fault identification of the power equipment. The technical problems that a large amount of manpower and material resources are needed to be input and the working efficiency is low in the traditional method for detecting the faults in the routing inspection of the transformer substation are solved. The fault identification and positioning method for the power equipment of the transformer substation can also be used for identifying the position of each power equipment in the transformer substation, so that the positioning accuracy of the power equipment of the transformer substation is improved, the operation of each power equipment is favorably monitored, and the stability of the normal operation of a power system is effectively guaranteed;
2. the fault identification and positioning device of the power equipment of the transformer substation adopts a data acquisition unit, a preprocessing unit, a construction model image unit, a feature extraction unit and an image classification unit to process the power equipment data for acquiring the construction fault identification model to obtain a fault identification model, an image to be detected of the power equipment to be detected is input into the fault identification model and is subjected to identification analysis through a fault identification analysis unit, whether the power equipment in the image to be detected is in fault or not is identified and analyzed, and if the fault is identified and analyzed, the position of the power equipment in the transformer substation is in fault, so that the fault identification and positioning device of the power equipment in the transformer substation can identify the position of the power equipment in the transformer substation in fault, the identification efficiency is high, and a large amount of manpower and material; and the data acquisition unit, the preprocessing unit and the model image construction unit are used for eliminating the interference of disordered images and irrelevant factors on fault identification, and the accuracy and efficiency of fault identification of the power equipment are greatly improved. The technical problems that a large amount of manpower and material resources are needed to be input and the working efficiency is low in the traditional method for detecting the faults in the routing inspection of the transformer substation are solved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.
Fig. 1 is a flowchart illustrating steps of a method for identifying and positioning a fault of a substation power device according to an embodiment of the present invention.
Fig. 2 is a flowchart illustrating steps of a point cloud data processing process of a fault identification and location method for substation power equipment according to an embodiment of the present invention.
Fig. 3 is a frame diagram of a fault identification and location device of substation power equipment according to an embodiment of the present invention.
Detailed Description
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the embodiments described below are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the application provides a fault identification and positioning method, a fault identification and positioning device and a fault identification and positioning device for power equipment of a transformer substation, a point cloud data of the power equipment is acquired by a laser scanner to construct an entity three-dimensional geometric model, the fault identification model is constructed by combining a convolutional neural network of artificial intelligence and deep learning aiming at the characteristics of the power equipment and different point cloud data of different transformer substations, the fault identification model is input by acquiring an image of the power equipment based on the laser scanner, whether the image of the power equipment breaks down or not is automatically identified, and the position of the fault is analyzed, so that the technical problems that the traditional method for detecting the fault by polling the transformer substation needs to be input greatly in manpower and material resources and the working efficiency is.
The first embodiment is as follows:
fig. 1 is a flowchart illustrating steps of a method for identifying and positioning a fault of a substation power device according to an embodiment of the present invention. As shown in fig. 1, an embodiment of the present invention provides a fault identification and location method for substation power equipment, including the following steps:
s1, data acquisition: acquiring three-dimensional point cloud data of all power equipment images in a transformer substation;
s2, data preprocessing: carrying out filtering pretreatment on the three-dimensional point cloud data to obtain point cloud data;
s3, constructing a model image: processing the point cloud data through resampling, data splicing and matching, and constructing the processed data into a three-dimensional model image;
s4, extracting image features: carrying out feature extraction on the model image to obtain image features;
s5, image classification: classifying the image features by adopting a convolutional neural network to obtain image feature classifications;
s6, constructing a fault identification model: training the image feature classification and the image features by adopting deep learning to obtain a fault recognition model;
s7, fault identification and analysis: and acquiring an image to be detected of one of the power equipment of the transformer substation, inputting the image to be detected into the fault identification model for identification and analysis, and obtaining the specific position of the power equipment without fault or fault.
In the embodiment of the invention, due to the fact that the detected power equipment of the transformer substation has the irregularity characteristic, in the data acquisition, the images of all the power equipment in the transformer substation are acquired in a three-dimensional laser scanner scanning mode. The image is three-dimensional point cloud data.
It should be noted that the data in the three-dimensional point cloud data includes three-dimensional data such as three-dimensional coordinates and texture information of the electrical equipment. And one of the transformer substations comprises power equipment such as a main transformer, a circuit breaker, an isolating switch, a current transformer, a voltage transformer, a lightning arrester, a capacitor, a reactor, a tubular bus, an overhead conductor, a cable, an insulator string, a porcelain bottle and the like. In this embodiment, the three-dimensional point cloud data includes data of all power devices in one substation.
In the implementation of the invention, in the data preprocessing process, because the data acquired by the laser scanner is accompanied by the noise or the noise, the three-dimensional point cloud data is subjected to denoising and smoothing filtering processing by adopting an octree method segmentation algorithm, and the topological relation is established according to the corresponding relation between the bounding box and the data point spatial distribution, so that the denoising and smoothing function is achieved; due to the limitation of the view angle and the environment of the instrument, after data are acquired, the laser scanner needs to perform initial registration and accurate registration to achieve the minimum registration error between different point clouds; the registration of the three-dimensional point cloud data greatly improves the registration speed and accuracy by adopting an improved ICP algorithm; aiming at the problem of large data volume of the scanned three-dimensional point cloud, on the premise of keeping data accuracy, data can be simplified through a minimum distance method, a uniform sampling method, a guard box method and a uniform and non-uniform network method, and the three-dimensional point cloud data can be simplified through the minimum distance method. Not only are outliers removed that are far from the surface, but the surface features are also enhanced.
In the implementation of the invention, in the process of constructing the model image, three-dimensional point cloud data of all power equipment images in the transformer substation is acquired through the three-dimensional laser image scanner by combining the characteristics of the power equipment and the characteristics of the environment where the power equipment is located, and the three-dimensional point cloud data is preprocessed, so that the interference caused by disordered data and irrelevant objects in the three-dimensional point cloud data is effectively eliminated, and the model image of the transformer substation can be quickly and accurately constructed. Specifically, the point cloud data obtained through the data preprocessing is disordered, and is processed through resampling, data splicing and matching, and the processed data is constructed into a three-dimensional model image.
It should be noted that the point cloud data is processed by the resampling and data stitching and matching, and then the data directly participates in the three-dimensional modeling, so as to obtain the more accurate model image. The model image is a model manufactured according to the obtained real image of the power equipment of the transformer substation, and scene features with higher discriminability can be extracted by combining a significant region in a scene of the transformer substation, so that a better scene classification effect is achieved.
In the embodiment of the invention, the extraction of the image features can be performed on the model image through a Local Binary Pattern (LBP), and can also be performed on the model image through a Histogram of Oriented Gradients (HOG) and a Haar feature pattern. Specifically, in the constructing of the fault identification model, texture information of an image and characteristics such as color and edge in a visible light image need to be combined to construct the fault identification model. In the process of extracting the image features, a Gist feature extraction mode is required to be adopted to extract features such as naturalness, openness and expansion of the image, the Gist feature extraction mode can better extract global features of the model image and reflect the spatial layout of the image, in the process of extracting the image features, a Gabor filtering mode is adopted to improve good direction selection and scale selection characteristics of the image and extract texture information of the image in different directions, and the Gabor filtering mode adopted in the process of extracting the image features is insensitive to illumination transformation and cannot influence the extraction of the image features in image rotation and deformation. Based on the particularity of the environment where the power equipment on the transformer substation is located, the Gist feature extraction mode and the Gabor filtering mode are combined to extract the image features of the model image in the image feature extraction process.
It should be noted that the Gabor filtering method may be a Gabor filter.
In an embodiment of the present invention, the image classification mainly uses a convolutional neural network to classify the acquired image features.
It should be noted that the convolutional neural network is a hierarchical model, and mainly includes an input layer, a convolutional layer, a pooling layer, a full-link layer, and an output layer. The convolutional neural network can be divided into two parts according to the function of each layer: the feature extractor is composed of an input layer, a convolutional layer and a pooling layer, the classifier is composed of a full connection layer and the input layer, the full connection layer in the image features is analyzed through the feature extractor of the convolutional neural network and the classifier, a classification result is output through normalization finger processing, and image classification processing of the image can be achieved ingeniously. The method comprises the steps that after feature extraction is carried out on a model image, the model image is input and transmitted to a first convolution layer, convolution is carried out, graph output is carried out in an activation mode, features of the image after filtering in the convolution layer are output and transmitted, each filter can give different features to help correct class prediction, parameter quantity of a subsequent pooling layer is further reduced, when the convolution layer extracts the features, a deeper convolution neural network can extract more specific features, and a shallower network can extract more shallow features. After the processing of the convolution layer and the pooling layer for many times, the output layer can generate output, information can be compared with each other to eliminate errors, and the accuracy of fault analysis through the fault recognition model is improved.
In the embodiment of the invention, the fault identification model for identifying the substation power equipment fault is obtained by training in the process of constructing the fault identification model based on a Gist feature extraction mode, a Gabor filter and a convolution neural network. Compared with the existing algorithms such as DBN, NN and SVM, experiments of the fault recognition model on an O & T outdoor scene image data set show that the outdoor scene image characteristics can be more effectively represented and higher resolution can be obtained, so that whether the power equipment in the tested substation breaks down or not can be detected, the detection efficiency is high, and the accuracy is also high.
In the embodiment of the invention, the image of the fault identification model comprises a visible light image, and in the fault identification analysis process, the acquired image to be detected is input into the fault identification model, and is subjected to processing, feature extraction and image classification and then is compared with the visible light image in a combined manner, so that whether a power device in the detected transformer substation is in fault and the accurate position of the fault is acquired. Specifically, the acquired image to be measured is an image shot under visible light and angles of horizontal and pitch angles. Among them, the deep learning may be preferably a convolutional neural network.
The method includes the steps that a to-be-detected image of power equipment of a transformer substation is obtained through a laser scanner, and the to-be-detected image is a laser point cloud three-dimensional modeling diagram; and performing image matching calculation on texture information obtained in the image to be detected by laser scanning and the image shot under the visible light, and achieving an accurate positioning effect according to the stable position of the image under the visible light.
The fault identification and positioning method of the power equipment of the transformer substation provided by the invention constructs the fault identification model through five steps of data acquisition, data preprocessing, model image construction, image feature extraction and image classification, the image to be detected of the power equipment of the transformer substation is input into the fault identification model, the fault identification model identifies and analyzes whether the power equipment in the image to be detected is in fault or not, and if the fault occurs, the fault identification and analysis result shows the position of the power equipment of the transformer substation. The fault identification and positioning method for the power equipment of the transformer substation can eliminate the interference of disordered images and irrelevant factors on fault identification, and greatly improves the accuracy and efficiency of fault identification of the power equipment. The technical problems that a large amount of manpower and material resources are needed to be input and the working efficiency is low in the traditional method for detecting the faults in the routing inspection of the transformer substation are solved. The fault identification and positioning method for the power equipment of the transformer substation can also be used for identifying the position of each power equipment in the transformer substation, improves the positioning accuracy of the power equipment of the transformer substation, is beneficial to monitoring the operation of each power equipment, and effectively ensures the stability of the normal operation of a power system.
In an embodiment of the invention, the three-dimensional point cloud data and the image to be measured are obtained by scanning power equipment through a three-dimensional laser scanner.
It should be noted that, in this embodiment, the three-dimensional laser image scanner may be used to model point cloud data, and the apparatus is small, convenient, safe, stable, and highly operable, and can establish a detailed and accurate three-dimensional image of the sensed area in a short time, so that the obtained power equipment image is a three-dimensional image.
Fig. 2 is a flowchart illustrating steps of a point cloud data processing process of a fault identification and location method for substation power equipment according to an embodiment of the present invention.
As shown in fig. 2, in an embodiment of the present invention, in the step S3, the processing of the point cloud data includes:
s31, simplifying and screening the point cloud data by adopting the resampled point cloud to obtain messy point cloud data;
s32, performing data splicing on the messy point cloud data through the data splicing and the matched target splicing and homonymous point mixed splicing method to obtain the spliced point cloud data;
and S33, unifying the spliced point cloud data to the same coordinate system by adopting point cloud registration to form the three-dimensional model image.
It should be noted that the resampling mainly unifies the collected point cloud data into the same coordinate system through the point cloud simplification, the target splicing and the homonymy point of the data splicing and matching, and the point cloud registration, so as to form a three-dimensional model. In this embodiment, in order to obtain a better image effect, a texture mapping function is adopted, and data is fully displayed in a model to obtain data such as different coordinate displacements and normal vectors, so as to prepare for accurate positioning analysis of the fault identification analysis.
In an embodiment of the present invention, in the step S7, the image of the fault identification model includes a visible light image, if the power equipment of the image to be detected has a fault, the image to be detected is input into the fault identification model, and the fault identification model is displayed on the visible light image after the image features are classified and analyzed, so as to obtain an accurate position of the fault of the image to be detected.
It should be noted that, the fault recognition model obtained by training the image feature classification and the image feature by using a deep learning technique has various models, and a Convolutional Neural Network (CNN) is a relatively classical one. The convolutional neural network model is a multilayer neural network, and successfully performs continuous dimensionality reduction on a large picture, so that the large picture can be trained. The CNN model is mainly composed of three parts: the first part is composed of a combination of n convolutional layers and a pooling layer, the second part is composed of a fully-connected multi-layer perceptron classifier, and the third part is composed of a fully-connected multi-layer perceptron classifier.
Example two:
fig. 3 is a frame diagram of a fault identification and location device of substation power equipment according to an embodiment of the present invention.
As shown in fig. 3, an embodiment of the present invention provides a fault identification and location device for substation power equipment, including:
the data acquisition unit 10 is used for acquiring three-dimensional point cloud data of all power equipment images in the transformer substation;
the preprocessing unit 20 is configured to perform filtering preprocessing on the three-dimensional point cloud data to obtain point cloud data;
a model image construction unit 30, configured to process the point cloud data through resampling and data stitching and matching, and construct a three-dimensional model image from the processed data;
a feature extraction unit 40, configured to perform feature extraction on the model image to obtain an image feature;
the image classification unit 50 is used for classifying the image features by adopting a convolutional neural network to obtain image feature classifications;
a fault identification model building unit 60, configured to train the image feature classification and the image features by using deep learning to obtain a fault identification model;
and the fault identification and analysis unit 70 is configured to obtain an image to be detected of one of the power devices of the substation, and the image to be detected is input into the fault identification model for identification and analysis to obtain a specific position where the power device is not faulty or faulty.
It should be noted that a three-dimensional laser scanner scanning mode is adopted to obtain three-dimensional point cloud data of all power equipment images in the substation. And processing the point cloud data through resampling, data splicing and matching, and then directly participating the data in three-dimensional modeling, thereby obtaining the more accurate model image. The model image is a model manufactured according to the obtained real image of the power equipment of the transformer substation, and scene features with higher discriminability can be extracted by combining a significant region in a scene of the transformer substation, so that a better scene classification effect is achieved. The convolutional neural network is a hierarchical model and mainly comprises an input layer, a convolutional layer, a pooling layer, a full-link layer and an output layer. The convolutional neural network can be divided into two parts according to the function of each layer: the feature extractor is composed of an input layer, a convolutional layer and a pooling layer, the classifier is composed of a full connection layer and the input layer, the full connection layer in the image features is analyzed through the feature extractor of the convolutional neural network and the classifier, a classification result is output through normalization finger processing, and image classification processing of the image can be achieved ingeniously. The method comprises the steps that after feature extraction is carried out on a model image, the model image is input and transmitted to a first convolution layer, convolution is carried out, graph output is carried out in an activation mode, features of the image after filtering in the convolution layer are output and transmitted, each filter can give different features to help correct class prediction, parameter quantity of a subsequent pooling layer is further reduced, when the convolution layer extracts the features, a deeper convolution neural network can extract more specific features, and a shallower network can extract more shallow features. After the processing of the convolution layer and the pooling layer for many times, the output layer can generate output, information can be compared with each other to eliminate errors, and the accuracy of fault analysis through the fault recognition model is improved.
In the embodiment of the present invention, the preprocessing unit 20 performs denoising and smoothing filtering on the three-dimensional point cloud data by using an octree segmentation algorithm to obtain the point cloud data.
It should be noted that, because the data acquired by the laser scanner is accompanied by noise points or noises, the three-dimensional point cloud data is denoised and smoothed by using an octree segmentation algorithm, and a topological relation is established according to a corresponding relation between a bounding box and data point spatial distribution, so as to achieve a denoising and smoothing function; due to the limitation of the view angle and the environment of the instrument, after data are acquired, the laser scanner needs to perform initial registration and accurate registration to achieve the minimum registration error between different point clouds; the registration of the three-dimensional point cloud data greatly improves the registration speed and accuracy by adopting an improved ICP algorithm; aiming at the problem of large data volume of the scanned three-dimensional point cloud, on the premise of keeping data accuracy, data can be simplified through a minimum distance method, a uniform sampling method, a guard box method and a uniform and non-uniform network method, and the three-dimensional point cloud data can be simplified through the minimum distance method. Not only are outliers removed that are far from the surface, but the surface features are also enhanced.
In an embodiment of the present invention, the model image constructing unit 30 includes a screening unit 31, a data stitching unit 32, and a three-dimensional modeling unit 33;
the screening unit 31 is configured to adopt the resampled point cloud to simplify and screen the point cloud data to obtain messy point cloud data;
the data splicing unit 32 is configured to perform data splicing on the messy point cloud data through the data splicing and a target splicing and homonymous point mixed splicing method of matching to obtain the spliced point cloud data;
and the three-dimensional modeling unit 33 is configured to unify the spliced point cloud data into the same coordinate system by using point cloud registration to form a three-dimensional model image.
It should be noted that the resampling mainly unifies the collected point cloud data into the same coordinate system through the point cloud simplification, the target splicing and the homonymy point of the data splicing and matching, and the point cloud registration, so as to form a three-dimensional model. In this embodiment, in order to obtain a better image effect, a texture mapping function is adopted, and data is fully displayed in a model to obtain data such as different coordinate displacements and normal vectors, so as to prepare for accurate positioning analysis of the fault identification analysis.
In the embodiment of the present invention, the feature extraction unit 40 extracts features of the naturalness, the openness, and the expansion of the model image by using a Gist feature extraction method to obtain image features; and in the process of extracting the image characteristics, a Gabor filtering mode is adopted to extract different textures of the image from the direction and the size of the model image.
It should be noted that, in the process of extracting image features, the Gist feature extraction method needs to be used to extract features of the image, such as naturalness, openness, and expansion degree, the Gist feature extraction method can better extract global features of the model image and reflect spatial layout of the image, in the process of extracting image features, the Gabor filtering method is used to improve good direction selection and scale selection characteristics of the image and extract texture information of the image in different directions, and the Gabor filtering method used in the process of extracting image features is insensitive to illumination transformation and will not affect the extracted image features in image rotation and deformation. Based on the particularity of the environment where the power equipment on the transformer substation is located, the Gist feature extraction mode and the Gabor filtering mode are combined to extract the image features of the model image in the image feature extraction process. The Gabor filtering method may be a Gabor filter.
The fault identification and positioning device for the power equipment of the transformer substation provided by the invention adopts the data acquisition unit, the preprocessing unit, the model construction image unit, the feature extraction unit and the image classification unit to process the power equipment data for constructing the fault identification model to obtain the fault identification model, the image to be detected of the power equipment to be detected is input into the fault identification model to be identified and analyzed through the fault identification and analysis unit, whether the power equipment in the image to be detected is in fault is identified and analyzed, and if the fault is identified and analyzed, the position of the power equipment in the transformer substation is in fault, so that the fault identification and positioning device for the power equipment in the transformer substation can identify the position of the power equipment in the transformer substation in fault, the identification efficiency is high, and a large amount of manpower and material resources are not required; and the data acquisition unit, the preprocessing unit and the model image construction unit are used for eliminating the interference of disordered images and irrelevant factors on fault identification, and the accuracy and efficiency of fault identification of the power equipment are greatly improved. The technical problems that a large amount of manpower and material resources are needed to be input and the working efficiency is low in the traditional method for detecting the faults in the routing inspection of the transformer substation are solved.
Example three:
the embodiment of the invention provides equipment, which comprises a processor and a memory;
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is used for executing the fault identification and positioning method of the substation power equipment according to the instructions in the program codes.
It should be noted that the processor is configured to execute the steps in the above-mentioned embodiment of the fault identification and location method for substation power equipment, such as steps S1 to S7 shown in fig. 1, according to the instructions in the program code. Alternatively, the processor, when executing the computer program, implements the functions of the modules/units in the above-described device embodiments, such as the functions of the units 10 to 70 shown in fig. 3.
Illustratively, a computer program may be partitioned into one or more modules/units, which are stored in a memory and executed by a processor to accomplish the present application. One or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution of a computer program in a terminal device.
The terminal device may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The terminal device may include, but is not limited to, a processor, a memory. Those skilled in the art will appreciate that the terminal device is not limited and may include more or fewer components than those shown, or some components may be combined, or different components, e.g., the terminal device may also include input output devices, network access devices, buses, etc.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable gate array (FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware component, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage may be an internal storage unit of the terminal device, such as a hard disk or a memory of the terminal device. The memory may also be an external storage device of the terminal device, such as a plug-in hard disk, a Smart Memory Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the terminal device. Further, the memory may also include both an internal storage unit of the terminal device and an external storage device. The memory is used for storing computer programs and other programs and data required by the terminal device. The memory may also be used to temporarily store data that has been output or is to be output.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a device (which may be a personal computer, a server, or a network device) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A fault identification and positioning method for substation power equipment is characterized by comprising the following steps:
s1, data acquisition: acquiring three-dimensional point cloud data of all power equipment images in a transformer substation;
s2, data preprocessing: carrying out filtering pretreatment on the three-dimensional point cloud data to obtain point cloud data;
s3, constructing a model image: processing the point cloud data through resampling, data splicing and matching, and constructing the processed data into a three-dimensional model image;
s4, extracting image features: carrying out feature extraction on the model image to obtain image features;
s5, image classification: classifying the image features by adopting a convolutional neural network to obtain image feature classifications;
s6, constructing a fault identification model: training the image feature classification and the image features by adopting deep learning to obtain a fault recognition model;
s7, fault identification and analysis: and acquiring an image to be detected of one of the power equipment of the transformer substation, inputting the image to be detected into the fault identification model for identification and analysis, and obtaining the specific position of the power equipment without fault or fault.
2. The fault identification and positioning method for the substation power equipment according to claim 1, wherein the three-dimensional point cloud data and the image to be measured are obtained by scanning the power equipment through a three-dimensional laser scanner.
3. The method for identifying and positioning the fault of the substation power equipment according to claim 1, wherein in the step S2, the three-dimensional point cloud data is denoised and smoothed by using an octree segmentation algorithm to obtain the point cloud data.
4. The method for identifying and locating the fault of the substation power equipment according to claim 1, wherein in the step S3, the processing of the point cloud data includes:
simplifying and screening the point cloud data by adopting the resampled point cloud to obtain messy point cloud data;
performing data splicing on the messy point cloud data through the data splicing and a target splicing and homonymous point mixed splicing method matched with the data splicing method to obtain the spliced point cloud data;
and unifying the spliced point cloud data to the same coordinate system by adopting point cloud registration to form the three-dimensional model image.
5. The fault identification and location method for the substation power equipment according to claim 1, wherein in the step S4, features of naturalness, openness and expansibility of the model image are extracted by adopting a Gist feature extraction method to obtain image features; and in the process of extracting the image characteristics, a Gabor filtering mode is adopted to extract different textures of the image from the direction and the size of the model image.
6. The method for identifying and positioning the fault of the substation power equipment according to claim 1, wherein in the step S7, the image of the fault identification model includes a visible light image, if the power equipment of the image to be detected has a fault, the image to be detected is input into the fault identification model, and the fault identification model is displayed on the visible light image after the image features are classified and analyzed, so as to obtain the accurate position of the fault of the image to be detected.
7. The utility model provides a fault identification positioner of transformer substation's power equipment which characterized in that includes:
the data acquisition unit is used for acquiring three-dimensional point cloud data of all power equipment images in the transformer substation;
the preprocessing unit is used for carrying out filtering preprocessing on the three-dimensional point cloud data to obtain point cloud data;
a model image constructing unit for processing the point cloud data through resampling, data splicing and matching and constructing the processed data into a three-dimensional model image;
the characteristic extraction unit is used for extracting the characteristics of the model image to obtain image characteristics;
the image classification unit is used for classifying the image features by adopting a convolutional neural network to obtain image feature classifications;
a fault recognition model building unit for training the image feature classification and the image features by adopting deep learning to obtain a fault recognition model;
and the fault identification and analysis unit is used for acquiring an image to be detected of one of the electric power equipment of the transformer substation, and the image to be detected is input into the fault identification model for identification and analysis to obtain the specific position of the electric power equipment without fault or fault.
8. The fault identification and positioning device of the substation power equipment according to claim 7, wherein the preprocessing unit performs denoising and smoothing filtering processing on the three-dimensional point cloud data by using an octree segmentation algorithm to obtain the point cloud data;
the feature extraction unit extracts features of the naturalness, the openness and the expansion of the model image by adopting a Gist feature extraction mode to obtain image features; and in the process of extracting the image characteristics, a Gabor filtering mode is adopted to extract different textures of the image from the direction and the size of the model image.
9. The fault identification and positioning device for the substation power equipment according to claim 7, wherein the construction model image unit comprises a screening unit, a data splicing unit and a three-dimensional modeling unit;
the screening unit is used for simplifying and screening the point cloud data by adopting the resampled point cloud to obtain messy point cloud data;
the data splicing unit is used for performing data splicing on the messy point cloud data through the data splicing, target splicing matched with the data splicing and a homonymous point mixed splicing method to obtain the spliced point cloud data;
and the three-dimensional modeling unit is used for unifying the spliced point cloud data into the same coordinate system by adopting point cloud registration to form a three-dimensional model image.
10. An apparatus comprising a processor and a memory;
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to execute the fault identification and location method of the substation power equipment according to any one of claims 1 to 6 according to instructions in the program code.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911384876.XA CN111144325A (en) | 2019-12-28 | 2019-12-28 | Fault identification and positioning method, device and equipment for power equipment of transformer substation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911384876.XA CN111144325A (en) | 2019-12-28 | 2019-12-28 | Fault identification and positioning method, device and equipment for power equipment of transformer substation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111144325A true CN111144325A (en) | 2020-05-12 |
Family
ID=70521321
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911384876.XA Pending CN111144325A (en) | 2019-12-28 | 2019-12-28 | Fault identification and positioning method, device and equipment for power equipment of transformer substation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111144325A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112419243A (en) * | 2020-11-11 | 2021-02-26 | 国网山东省电力公司青岛供电公司 | Power distribution room equipment fault identification method based on infrared image analysis |
| CN112614059A (en) * | 2020-11-30 | 2021-04-06 | 国网北京市电力公司 | Transformer substation detection method and device, storage medium and processor |
| CN112714284A (en) * | 2020-12-22 | 2021-04-27 | 全球能源互联网研究院有限公司 | Power equipment detection method and device and mobile terminal |
| CN112907421A (en) * | 2021-02-24 | 2021-06-04 | 中煤科工集团重庆智慧城市科技研究院有限公司 | Service scene acquisition system and method based on spatial analysis |
| CN112949445A (en) * | 2021-02-24 | 2021-06-11 | 中煤科工集团重庆智慧城市科技研究院有限公司 | Urban management emergency linkage system and method based on spatial relationship |
| CN113191336A (en) * | 2021-06-04 | 2021-07-30 | 绍兴建元电力集团有限公司 | Electric power hidden danger identification method and system based on image identification |
| CN113361686A (en) * | 2021-05-27 | 2021-09-07 | 广西大学 | Multilayer heterogeneous multi-mode convolutional neural network integrated robot inspection method |
| CN113538570A (en) * | 2021-09-15 | 2021-10-22 | 南方电网数字电网研究院有限公司 | Positioning method and device of power equipment, computer equipment and storage medium |
| CN113538660A (en) * | 2021-07-06 | 2021-10-22 | 国网江苏省电力有限公司建设分公司 | Power transmission and transformation project acceptance method based on BIM and point cloud measurement |
| TWI810863B (en) * | 2022-03-24 | 2023-08-01 | 中華電信股份有限公司 | An abnormal inspection system and method for power generation equipment and computer-readable medium thereof |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1195875A2 (en) * | 2000-09-22 | 2002-04-10 | ABB Substation Automation Oy | Method for identification of a faulting or faulted sending end or feeder branch in an electrical distribution system such as a compensated network |
| CN104598920A (en) * | 2014-12-30 | 2015-05-06 | 中国人民解放军国防科学技术大学 | Scene classification method based on Gist characteristics and extreme learning machine |
| CN107170045A (en) * | 2017-03-21 | 2017-09-15 | 国网湖北省电力公司检修公司 | The method being modeled based on cloud data to substation transformer |
| CN109389180A (en) * | 2018-10-30 | 2019-02-26 | 国网四川省电力公司广元供电公司 | A power equipment image-recognizing method and inspection robot based on deep learning |
| CN110471376A (en) * | 2019-07-10 | 2019-11-19 | 深圳市乾行达科技有限公司 | A kind of industry spot fault detection method and equipment |
-
2019
- 2019-12-28 CN CN201911384876.XA patent/CN111144325A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1195875A2 (en) * | 2000-09-22 | 2002-04-10 | ABB Substation Automation Oy | Method for identification of a faulting or faulted sending end or feeder branch in an electrical distribution system such as a compensated network |
| CN104598920A (en) * | 2014-12-30 | 2015-05-06 | 中国人民解放军国防科学技术大学 | Scene classification method based on Gist characteristics and extreme learning machine |
| CN107170045A (en) * | 2017-03-21 | 2017-09-15 | 国网湖北省电力公司检修公司 | The method being modeled based on cloud data to substation transformer |
| CN109389180A (en) * | 2018-10-30 | 2019-02-26 | 国网四川省电力公司广元供电公司 | A power equipment image-recognizing method and inspection robot based on deep learning |
| CN110471376A (en) * | 2019-07-10 | 2019-11-19 | 深圳市乾行达科技有限公司 | A kind of industry spot fault detection method and equipment |
Non-Patent Citations (1)
| Title |
|---|
| 陈家斌: "变压器", vol. 1, 中国电力出版社, pages: 443 - 444 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112419243B (en) * | 2020-11-11 | 2023-08-11 | 国网山东省电力公司青岛供电公司 | Power distribution room equipment fault identification method based on infrared image analysis |
| CN112419243A (en) * | 2020-11-11 | 2021-02-26 | 国网山东省电力公司青岛供电公司 | Power distribution room equipment fault identification method based on infrared image analysis |
| CN112614059A (en) * | 2020-11-30 | 2021-04-06 | 国网北京市电力公司 | Transformer substation detection method and device, storage medium and processor |
| CN112714284A (en) * | 2020-12-22 | 2021-04-27 | 全球能源互联网研究院有限公司 | Power equipment detection method and device and mobile terminal |
| CN112907421A (en) * | 2021-02-24 | 2021-06-04 | 中煤科工集团重庆智慧城市科技研究院有限公司 | Service scene acquisition system and method based on spatial analysis |
| CN112949445A (en) * | 2021-02-24 | 2021-06-11 | 中煤科工集团重庆智慧城市科技研究院有限公司 | Urban management emergency linkage system and method based on spatial relationship |
| CN112949445B (en) * | 2021-02-24 | 2024-04-05 | 中煤科工集团重庆智慧城市科技研究院有限公司 | Urban management emergency linkage system and method based on spatial relationship |
| CN113361686A (en) * | 2021-05-27 | 2021-09-07 | 广西大学 | Multilayer heterogeneous multi-mode convolutional neural network integrated robot inspection method |
| CN113191336B (en) * | 2021-06-04 | 2022-01-14 | 绍兴建元电力集团有限公司 | Electric power hidden danger identification method and system based on image identification |
| CN113191336A (en) * | 2021-06-04 | 2021-07-30 | 绍兴建元电力集团有限公司 | Electric power hidden danger identification method and system based on image identification |
| CN113538660A (en) * | 2021-07-06 | 2021-10-22 | 国网江苏省电力有限公司建设分公司 | Power transmission and transformation project acceptance method based on BIM and point cloud measurement |
| CN113538570A (en) * | 2021-09-15 | 2021-10-22 | 南方电网数字电网研究院有限公司 | Positioning method and device of power equipment, computer equipment and storage medium |
| TWI810863B (en) * | 2022-03-24 | 2023-08-01 | 中華電信股份有限公司 | An abnormal inspection system and method for power generation equipment and computer-readable medium thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111144325A (en) | Fault identification and positioning method, device and equipment for power equipment of transformer substation | |
| CN108764048B (en) | Face key point detection method and device | |
| Yang et al. | Voxel-based extraction of transmission lines from airborne lidar point cloud data | |
| CN112233249B (en) | B spline surface fitting method and device based on dense point cloud | |
| CN104299260A (en) | Contact network three-dimensional reconstruction method based on SIFT and LBP point cloud registration | |
| CN110751097B (en) | Semi-supervised three-dimensional point cloud gesture key point detection method | |
| CN109580004A (en) | A kind of temperature checking method and device | |
| CN110133443B (en) | Power transmission line component detection method, system and device based on parallel vision | |
| CN112365503A (en) | Point cloud data-based transformer substation scene segmentation method | |
| CN116229007B (en) | Four-dimensional digital image construction method, device, equipment and medium using BIM modeling | |
| Xie et al. | Fabric defect detection method combing image pyramid and direction template | |
| CN111402224A (en) | Target identification method for power equipment | |
| CN110704652A (en) | Vehicle image fine-grained retrieval method and device based on multiple attention mechanism | |
| CN114219855A (en) | Point cloud normal vector estimation method and device, computer equipment and storage medium | |
| CN112001317A (en) | Lead defect identification method and system based on semantic information and terminal equipment | |
| Zhao et al. | Region-based saliency estimation for 3D shape analysis and understanding | |
| Prasad et al. | Mobile plant species classification: a low computational aproach | |
| US11816857B2 (en) | Methods and apparatus for generating point cloud histograms | |
| Agus et al. | Shape analysis of 3D nanoscale reconstructions of brain cell nuclear envelopes by implicit and explicit parametric representations | |
| US20210150078A1 (en) | Reconstructing an object | |
| Huang et al. | A method for classifying tube structures based on shape descriptors and a random forest classifier | |
| CN116452604A (en) | Complex substation scene segmentation method, device and storage medium | |
| CN115019396A (en) | Learning state monitoring method, device, equipment and medium | |
| CN114565629A (en) | Large skin edge defect detection method based on multi-scale neighborhood | |
| CN110895679B (en) | Machine vision image data processing method and device |
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 |