CN114842295A - Method and device for obtaining insulator fault detection model and electronic equipment - Google Patents
Method and device for obtaining insulator fault detection model and electronic equipment Download PDFInfo
- Publication number
- CN114842295A CN114842295A CN202210476401.9A CN202210476401A CN114842295A CN 114842295 A CN114842295 A CN 114842295A CN 202210476401 A CN202210476401 A CN 202210476401A CN 114842295 A CN114842295 A CN 114842295A
- Authority
- CN
- China
- Prior art keywords
- insulator
- image
- fault detection
- detection model
- obtaining
- 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
- 239000012212 insulator Substances 0.000 title claims abstract description 297
- 238000001514 detection method Methods 0.000 title claims abstract description 101
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000012549 training Methods 0.000 claims abstract description 53
- 238000012706 support-vector machine Methods 0.000 claims abstract description 50
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 21
- 238000000605 extraction Methods 0.000 claims abstract description 12
- 230000015654 memory Effects 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 20
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000012795 verification Methods 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 16
- 238000010586 diagram Methods 0.000 description 9
- 238000007689 inspection Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 239000000725 suspension Substances 0.000 description 5
- 238000013135 deep learning Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 3
- 238000011179 visual inspection Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013515 script Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 235000002566 Capsicum Nutrition 0.000 description 1
- 239000006002 Pepper Substances 0.000 description 1
- 235000016761 Piper aduncum Nutrition 0.000 description 1
- 235000017804 Piper guineense Nutrition 0.000 description 1
- 244000203593 Piper nigrum Species 0.000 description 1
- 235000008184 Piper nigrum Nutrition 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005684 electric field Effects 0.000 description 1
- 238000010292 electrical insulation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004643 material aging Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000002904 solvent Substances 0.000 description 1
- 230000035882 stress Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
- G06V10/42—Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- 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
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The application provides a method and a device for obtaining an insulator fault detection model, electronic equipment and a computer readable storage medium; the method comprises the following steps: obtaining an insulator image carrying an insulator label; the insulator tag comprises an insulator fault type and the position of the insulator in a contact network; performing feature extraction on the insulator image based on a machine vision algorithm to obtain corresponding image features; constructing a training sample based on the image characteristics and the corresponding insulator label; training a support vector machine model by using the training sample to obtain a corresponding insulator fault detection model; the insulator fault detection model is used for classifying the image to be detected to obtain the fault type and the insulator position of the insulator in the image to be detected. Through the method and the device, the insulator fault detection model capable of efficiently and accurately detecting the insulator fault can be obtained.
Description
Technical Field
The present disclosure relates to computer technologies, and in particular, to a method and an apparatus for obtaining an insulator fault detection model, and an electronic device.
Background
The contact net is one of main power supply unit in urban rail transit, comprises basic pillar, cantilever bearing structure (including positioner), contact net suspension three subsystem. According to the upper suspension mode, the overhead contact system can be divided into a rigid suspension overhead contact system and a flexible suspension overhead contact system. The insulator is one of important parts in a contact net suspension device and plays a role in electrical insulation and wire connection. Most flexible contact net insulators are exposed outdoors, the working environment is complex and changeable, and the insulators are very easy to have faults of material aging, damage, chip falling and the like due to long-term sun and rain exposure, strong chemical corrosion mechanical stress and electric field load; the fault of the rigid contact net insulator is not over-current due to the quality of the insulator on one hand, and over-current instantaneous breakdown is generated due to the reasons of dust, water scale, flowing water line formation and the like on the other hand. Insulator faults not only can cause the function failure of the insulator, but also easily cause contact network line safety accidents, so in order to ensure the reliability of the contact network line, the regular inspection of the insulator is an important maintenance procedure.
The traditional inspection mode mainly depends on manual inspection, visual inspection is carried out through manual work, the detection efficiency is low, the time consumption is long, the safety of detection personnel is difficult to guarantee, and whether inspection can be carried out easily and is also influenced by environmental factors. The appearance of inspection robots and vehicle-mounted video monitoring equipment makes it possible to take insulator images instead of the original visual inspection. Because the track traffic line is complicated, the insulator quantity is huge, can generate a large amount of insulator images through shooing, and the method efficiency of carrying out artifical visual inspection through transmitting back the image is not high, and the inspector faces a large amount of pictures for a long time, and is tired easily, and the possibility that causes the false retrieval is great.
Disclosure of Invention
The embodiment of the application provides a method and a device for obtaining an insulator fault detection model, electronic equipment and a computer readable storage medium, and the insulator fault detection model capable of efficiently and accurately detecting insulator faults can be obtained.
The technical scheme of the embodiment of the application is realized as follows:
the embodiment of the application provides a method for obtaining an insulator fault detection model, which comprises the following steps:
obtaining an insulator image carrying an insulator label; the insulator tag comprises an insulator fault type and the position of the insulator in a contact network;
performing feature extraction on the insulator image based on a machine vision algorithm to obtain corresponding image features;
constructing a training sample based on the image characteristics and the corresponding insulator label;
training a support vector machine model by using the training sample to obtain a corresponding insulator fault detection model;
the insulator fault detection model is used for classifying the image to be detected to obtain the fault type and the insulator position of the insulator in the image to be detected.
In the foregoing solution, before obtaining the insulator image carrying the insulator tag, the method includes:
obtaining an initial insulator image;
and adding an insulator label to the initial insulator image to obtain an insulator image carrying the insulator label.
In the foregoing solution, the obtaining an initial insulator image includes:
acquiring a shot image obtained after the image shooting equipment shoots the contact network area;
and preprocessing the shot image to obtain the initial insulator image.
In the above scheme, the preprocessing the initial insulator image includes:
performing color space conversion processing on the initial insulator image;
and/or the presence of a gas in the gas,
performing Gaussian filtering processing on the initial insulator image;
and/or the presence of a gas in the gas,
and carrying out image enhancement processing on the initial insulator image.
In the foregoing solution, the training a support vector machine model by using the training sample to obtain a corresponding insulator fault detection model includes:
inputting the image features into the support vector machine model;
classifying based on the image features through the support vector machine model to obtain a prediction classification result, wherein the prediction classification result comprises a prediction fault type and a prediction position;
determining an error between the predicted classification result and the insulator label;
training the support vector machine model based on the error.
In the foregoing solution, after the training of the support vector machine model based on the error, the method further includes:
and (3) inspecting the support vector machine model by using a maximum entropy model and a verification data set to obtain an insulator fault detection model meeting the precision condition.
In the above scheme, the method further comprises:
obtaining an image to be detected;
performing feature extraction on the image to be detected based on a machine vision algorithm to obtain corresponding features of the image to be detected;
classifying the characteristics of the image to be detected through the insulator fault detection model to obtain the fault type and the insulator position of the insulator in the image to be detected.
The embodiment of the application provides an obtaining device of insulator fault detection model, includes:
the acquisition module is used for acquiring an insulator image carrying the insulator label; the insulator tag comprises an insulator fault type and the position of the insulator in a contact network;
the characteristic extraction module is used for extracting the characteristics of the insulator images based on a machine vision algorithm to obtain corresponding image characteristics;
the construction module is used for constructing a training sample based on the image characteristics and the corresponding insulator label;
the training module is used for training a support vector machine model by using the training sample to obtain a corresponding insulator fault detection model;
the insulator fault detection model is used for classifying the image to be detected to obtain the fault type and the insulator position of the insulator in the image to be detected.
An embodiment of the present application provides an electronic device, including:
a memory for storing executable instructions;
and the processor is used for realizing the method for obtaining the insulator fault detection model provided by the embodiment of the application when the executable instructions stored in the memory are executed.
The embodiment of the application provides a computer-readable storage medium, which stores executable instructions for causing a processor to execute the computer-readable storage medium, so as to implement the method for obtaining the insulator fault detection model provided by the embodiment of the application.
According to the method, the insulator image carrying the insulator label is obtained, wherein the insulator label comprises the insulator fault type and the position of the insulator in a contact network; the method comprises the steps of extracting the characteristics of the insulator image based on a machine vision algorithm to obtain corresponding image characteristics, constructing a training sample based on the image characteristics and a corresponding insulator label, training a support vector machine model by using the training sample to obtain a corresponding insulator fault detection model, and obtaining the insulator fault detection model by combining machine vision and the support vector machine, so that a model with higher precision can be obtained by using smaller data training, and the fault detection of the insulator continued by using the model is more efficient and accurate.
Drawings
Fig. 1 is an alternative structural schematic diagram of an acquisition system of an insulator fault detection model provided in an embodiment of the present application;
fig. 2 is an alternative structural schematic diagram of an electronic device provided in an embodiment of the present application;
fig. 3 is an alternative schematic flow chart of a method for obtaining an insulator fault detection model according to an embodiment of the present disclosure;
FIG. 4 is a schematic flow chart of an alternative process of steps prior to step 301 provided herein;
FIG. 5 is a schematic diagram illustrating an alternative detailed flow of step 304 provided by an embodiment of the present application;
FIG. 6 is an alternative schematic diagram of a two-dimensional classification of a support vector machine model provided by an embodiment of the present application;
fig. 7 is an alternative schematic diagram of the conversion of the SVM nonlinear classification provided by the embodiment of the present application into the high-dimensional hyperplane linear classification.
Detailed Description
In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be described in further detail with reference to the attached drawings, the described embodiments should not be considered as limiting the present application, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.
In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict.
In the following description, references to the terms "first \ second \ third" are only to distinguish similar objects and do not denote a particular order, but rather the terms "first \ second \ third" are used to interchange specific orders or sequences, where appropriate, so as to enable the embodiments of the application described herein to be practiced in other than the order shown or described herein.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the present application only and is not intended to be limiting of the application.
At present, some researchers combine technologies such as machine vision, machine learning and deep learning to carry out intelligent fault detection on insulators. The detection method based on machine vision mainly cuts the insulator from a complex background by utilizing the characteristics of the color form and the like of the insulator, and then identifies the defects of the insulator through a mathematical model. The quality of the final detection result of the method often depends on the quality of image segmentation to a great extent. Although thousands of image segmentation methods exist, the universality of the existing segmentation method needs to be improved, and especially under the condition that the background of an image is very complex, complete and effective segmentation is difficult to realize; the detection method based on machine learning utilizes an image processing technology to extract the characteristics of the insulator for identification and detection. The detection algorithm of the method needs to extract specific features in a specific scene, the extracted features are too single, diversity and good generalization capability are not provided, and the calculation cost for realizing insulator positioning in a clustering or sliding window mode is relatively high; the insulator fault detection method based on deep learning mainly directly applies a deep learning detection algorithm to an insulator fault scene, insulator prior information is not fused to optimize a model, and detection accuracy is low. In addition, the deep learning model training process is large in calculation amount and long in time consumption.
In summary, the existing insulator fault detection method has the following problems: 1. the manual inspection has low efficiency, long time consumption, poor safety and easy environmental influence; 2. the intelligent fault detection technology based on image processing, machine learning and deep learning has large data calculation amount and low detection precision; 3. the intelligent detection technology cannot solve the problem of nonlinearity existing in the insulator fault identification process, and false detection exist to a certain extent.
Based on this, embodiments of the present application provide a method and an apparatus for obtaining an insulator fault detection model, an electronic device, and a computer-readable storage medium, which can obtain an insulator fault detection model that can efficiently and accurately perform insulator fault detection.
First, a system for obtaining an insulator fault detection model provided in an embodiment of the present application is described, referring to fig. 1, where fig. 1 is an optional schematic structural diagram of a system 100 for obtaining an insulator fault detection model provided in an embodiment of the present application, and in order to support an obtaining application of an insulator fault detection model, a terminal 103 is connected to a server 101 through a network 102. In some embodiments, the terminal 103 may be, but is not limited to, a laptop, a tablet, a desktop computer, a smart phone, a dedicated messaging device, a portable gaming device, a smart speaker, a smart watch, and the like. The server 101 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN) service, and a big data and artificial intelligence platform. The network 102 may be a wide area network or a local area network, or a combination of both. The terminal 103 and the server 101 may be directly or indirectly connected through wired or wireless communication, and the embodiment of the present application is not limited thereto.
The server 101 is configured to send the insulator image with the insulator tag to the terminal 103.
The terminal 103 is used for obtaining an insulator image carrying the insulator label; the insulator tag comprises an insulator fault type and the position of the insulator in a contact network; performing feature extraction on the insulator image based on a machine vision algorithm to obtain corresponding image features; constructing a training sample based on the image characteristics and the corresponding insulator label; training a support vector machine model by using the training sample to obtain a corresponding insulator fault detection model; the insulator fault detection model is used for classifying the image to be detected to obtain the fault type and the insulator position of the insulator in the image to be detected.
Next, an electronic device for implementing the method for obtaining the insulator fault detection model according to the embodiment of the present application is described, referring to fig. 2, fig. 2 is an optional schematic structural diagram of the electronic device 200 according to the embodiment of the present application, and in practical applications, the electronic device 200 may be implemented as the terminal 103 or the server 101 in fig. 1, and the electronic device is taken as the terminal 103 shown in fig. 1 as an example, so that the electronic device for implementing the method for obtaining the insulator fault detection model according to the embodiment of the present application is described. The electronic device 200 shown in fig. 2 includes: at least one processor 201, memory 205, at least one network interface 202, and a user interface 203. The various components in the electronic device 200 are coupled together by a bus system 204. It is understood that the bus system 204 is used to enable communications among the components. The bus system 204 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as bus system 204 in fig. 2.
The Processor 201 may be an integrated circuit chip having Signal processing capabilities, such as a general purpose Processor, a Digital Signal Processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like, wherein the general purpose Processor may be a microprocessor or any conventional Processor, or the like.
The user interface 203 includes one or more output devices 2031, including one or more speakers and/or one or more visual display screens, that enable the presentation of media content. The user interface 203 also includes one or more input devices 2032 including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.
The memory 205 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid state memory, hard disk drives, optical disk drives, and the like. Memory 205 may optionally include one or more storage devices physically located remote from processor 201.
The memory 205 includes either volatile memory or nonvolatile memory, and may also include both volatile and nonvolatile memory. The nonvolatile Memory may be a Read Only Memory (ROM), and the volatile Memory may be a Random Access Memory (RAM). The memory 205 described in embodiments herein is intended to comprise any suitable type of memory.
In some embodiments, the memory 205 is capable of storing data, examples of which include programs, modules, and data structures, or a subset or superset thereof, to support various operations, in embodiments of the present application, the memory 205 stores an operating system 2051, a network communication module 2052, a presentation module 2053, an input processing module 2054, and an insulator failure detection model obtaining device 2055; in particular, the amount of the solvent to be used,
an operating system 2051, which includes system programs for handling various basic system services and performing hardware-related tasks, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and for handling hardware-based tasks;
a network communication module 2052 for communicating to other computing devices via one or more (wired or wireless) network interfaces 202, exemplary network interfaces 202 including: bluetooth, wireless compatibility authentication (WiFi), and Universal Serial Bus (USB), etc.;
a presentation module 2053 for enabling presentation of information (e.g., user interfaces for operating peripherals and displaying content and information) via one or more output devices 2031 (e.g., display screens, speakers, etc.) associated with the user interface 203;
an input processing module 2054 for detecting one or more user inputs or interactions from one of the one or more input devices 2032 and for translating the detected inputs or interactions.
In some embodiments, the obtaining device of the insulator fault detection model provided in this embodiment of the present application may be implemented in a software manner, and fig. 2 illustrates the obtaining device 2055 of the insulator fault detection model stored in the memory 205, which may be software in the form of programs and plug-ins, and includes the following software modules: the first presentation module 20551, the detection module 20552, the determination module 20553, and the second presentation module 20554, which are logical and thus may be arbitrarily combined or further divided depending on the functionality implemented. The functions of the respective modules will be explained below.
In other embodiments, the obtaining Device of the insulator fault detection model provided in this embodiment may be implemented in hardware, and as an example, the obtaining Device of the insulator fault detection model provided in this embodiment may be a processor in the form of a hardware decoding processor, which is programmed to execute the obtaining method of the insulator fault detection model provided in this embodiment, for example, the processor in the form of the hardware decoding processor may be implemented by one or more Application Specific Integrated Circuits (ASICs), DSPs, Programmable Logic Devices (PLDs), Complex Programmable Logic Devices (CPLDs), Field Programmable Gate Arrays (FPGAs), or other electronic components.
The method for obtaining the insulator fault detection model provided by the embodiment of the present application will be described below with reference to exemplary applications and implementations of the terminal provided by the embodiment of the present application.
Referring to fig. 3, fig. 3 is an optional flowchart of a method for obtaining an insulator fault detection model according to an embodiment of the present application, which will be described with reference to the steps shown in fig. 3.
301, obtaining an insulator image carrying an insulator label; the insulator tag comprises an insulator fault type and the position of the insulator in a contact network;
and 304, training the support vector machine model by using the training sample to obtain a corresponding insulator fault detection model. The insulator fault detection model is used for classifying the image to be detected to obtain the fault type and the insulator position of the insulator in the image to be detected.
In practical implementation, the insulator image carrying the insulator tag is an image obtained by processing an area where the contact network is located after shooting the area. Specifically, in some embodiments, referring to fig. 4, fig. 4 is an optional flowchart of steps before step 301 provided in the present application, and before step 301, the following may also be performed:
and 402, adding an insulator label to the initial insulator image to obtain an insulator image carrying the insulator label.
Here, the initial insulator image may be a processed image with an insulator obtained from an existing database, or may be an image obtained by processing a captured image. In some embodiments, step 401 may be implemented as follows: acquiring a shot image obtained after the image shooting equipment shoots the contact network area; and preprocessing the shot image to obtain the initial insulator image.
The image shooting equipment comprises but is not limited to an aerial vehicle, an inspection robot, a vehicle-mounted video monitoring device and the like. In actual implementation, the area where the contact net is located can be shot by using equipment such as an aerial photography aircraft, an inspection robot or a vehicle-mounted video monitoring device, and a corresponding shot image is obtained. And after the shot image is obtained, preprocessing the shot image to obtain a preprocessed initial insulator image. In some embodiments, preprocessing the captured image may be performed by: performing color space conversion processing on the initial insulator image; and/or, performing Gaussian filtering processing on the initial insulator image; and/or performing image enhancement processing on the initial insulator image.
Specifically, the terminal may perform Hue Saturation Value (HSV) color space conversion on the shot, and eliminate a luminance error of the shot image using histogram equalization. The terminal can also adopt Gaussian filtering to filter Gaussian noise of the shot image, or filter salt and pepper noise of the shot image through a self-adaptive median filter. The terminal can also carry out sharpening processing on the shot image by adopting a second-order differentiation method so as to enhance the edge and detail information of the shot image.
And then, after the terminal obtains the preprocessed initial insulator image, adding an insulator label to the initial insulator image to obtain an insulator image carrying the insulator label. It should be noted that there are multiple initial insulator images obtained in the embodiment of the present application, including a normal insulator image and a faulty insulator image, and images of the same insulator in different time periods and different backgrounds. The insulator label printed on the insulator image at least comprises the fault type of the insulator and the position of the insulator in a contact network. In some embodiments, the insulator tag further includes information such as image capture time and image capture height.
In actual implementation, after the terminal obtains the insulator image carrying the insulator label, the terminal performs feature extraction on the insulator image based on a machine vision algorithm to obtain corresponding image features. Here, the machine vision algorithms include, but are not limited to, HOG, SIFT, SURF, ORB, LBP, HAAR, and the like. The Support Vector Machine (SVM) model related in the embodiment of the application can be obtained by selecting a proper kernel function structure according to actual needs. Specifically, the common kernel functions of the support vector machine include polynomial kernel functions, radial basis kernel functions RBF, laplacian kernel functions, Sigmoid kernel functions and the like, wherein the radial basis kernel functions RBF can be used for solving a nonlinear problem; respectively selecting different kernel functions to construct an SVM model, wherein the model with the best result is a prediction model; further, when the kernel function is used for generating the identification model, the kernel coefficient and the error punishment factor are comprehensively considered, the identification model is used for detecting the insulator of the training data, and the two parameters with the best detection effect are used as the optimal solutions of the parameters of the generated model. The support vector machine belongs to a machine learning algorithm, and aims to research how to improve the performance of a system by using experience through a calculation means. In the insulator image detection, the previous image experience data can be used for generating a corresponding model and a learning algorithm, and the quality of the insulator can be judged according to the model when a new image is contacted next time. The learning strategy of the algorithm is to maximize the classification interval, construct the optimal classification by using the classification interval, improve the generalization capability of the learner, better solve the problems of nonlinearity, high dimensional number, local minimum point and the like, and convert the complex problem into a convex quadratic programming problem. The algorithm can continuously perfect itself in actual operation and can be suitable for complex insulator images. The maximum entropy model is the model with the maximum conditional entropy under certain constraint, and can be used for judging the quality of the model prediction result.
In practical implementation, referring to fig. 5, fig. 5 is an optional detailed flowchart of step 304 provided in an embodiment of the present application, and step 304 may be implemented as follows:
In practical implementation, the terminal inputs the image features into the support vector machine model, and the image features are classified through the support vector machine model to obtain a corresponding prediction classification result. Here, the support vector machine model will classify the type of insulator fault and the position of the insulator for the image features. And after the support vector machine is obtained for classification, obtaining a prediction classification result, wherein the prediction classification result comprises a prediction fault type and a prediction position. Next, the terminal determines an error between the predicted classification result and the insulator tag. Here, the terminal determines a first error between the predicted fault type and the insulator fault type in the insulator tag and a second error between the predicted position and the position of the insulator in the insulator tag in the catenary, respectively, and obtains an error between the predicted classification result and the insulator tag based on the first error and the second error. Here, the terminal may assign weights to the insulator fault type and the position of the insulator in the catenary, that is, assign a first weight to the insulator fault type, assign a second weight to the position of the insulator in the catenary, perform weighted summation based on the first error, the first weight, the second error, and the second weight, and use the obtained value as an error between the prediction classification result and the insulator label.
It should be noted that the core idea of SVM is to construct a maximum-spaced classification hyperplane, so that the two types of samples are distributed on both sides of the classification plane. The principle of the fault diagnosis based on the hyperplane is as follows: the hyperplane can separate normal insulator data from insulator data with faults, and the two types of data are respectively positioned on one side of the hyperplane. On the fault side of the hyperplane, the farther the test data is away from the hyperplane, the greater the fault probability is; and the farther the data is away from the hyperplane, the smaller the fault probability is. The standard SVM is to find an optimal classification surface which can correctly classify two types of samples and ensure the maximum classification interval for the two types of samples which can be linearly classified. Two types of samples were:
(x 1 ,y 1 ),(x 2 ,y 2 ),...(x i ,y i )
x i ∈R n ,y i ∈{-1,1}
i＝1,2,...,l (1)
wherein R is the total number of training samples; n is the dimension of the sample space; x is the number of i Is a sample space vector; y is i Is a category label for the sample. The classification hyperplane is w · x + b ═ 0, see fig. 6, and fig. 6 is an alternative schematic diagram of the two-dimensional classification of the support vector machine model provided in the embodiment of the present application. As shown in fig. 6, where w is the normal vector of the optimal hyperplane; b is an offset; r 1 Upper and R 2 The values of the first dimension and the second dimension are two, respectively.
Referring to fig. 7, fig. 7 is an optional schematic diagram of converting an SVM nonlinear classification provided in the embodiment of the present application into a high-dimensional hyperplane linear classification, and for a case of nonlinear separable, a solution problem of an optimal hyperplane is converted into a constraint programming problem of equation (2):
the problem of constructing the optimal hyperplane can be converted into a dual quadratic programming problem as shown in formula (3) by defining Lagrange function in the formula (2):
the final optimal hyperplane function is:
the SVM model based on the training samples has the following specific training process: 1) converting an insulator fault detection model into a linear/nonlinear programming problem meeting constraints; 2) selecting a proper decision function to solve the linear/nonlinear programming problem, wherein the used decision function is called a hyperplane; 3) and classifying the collected insulator data based on the hyperplane to obtain an insulator fault detection model.
In some embodiments, after step 504, it may further be performed: and (3) detecting the support vector machine model by utilizing a maximum entropy model and a verification sample set to obtain an insulator fault detection model meeting the precision condition.
In actual implementation, the terminal inputs the verification sample set into the insulator fault detection model to obtain an insulator fault detection result; and detecting the detection model by using the maximum entropy model and the verification sample set, recognizing the model if the accuracy requirement is met, otherwise, repeating the third step and the fourth step again, and finally obtaining the model for detecting the insulator fault. It should be noted that the obtaining manner of the verification sample set is the same as the obtaining manner of the training sample set, and is not described herein again.
It should be noted that the maximum entropy model is a model with the maximum conditional entropy under a certain constraint. Maximum entropy model detection is to select the best classification model by using the maximum entropy principle. The principle is as follows: given a data set: τ { (x) 1 ,y 1 ),(x 2 ,y 2 ),…,(x i ,y i ) Get joint distributions from given datasets
And the empirical distribution of the edge distribution p (x):
where v (X ═ X, Y ═ Y) denotes the frequency of occurrence of samples in the dataset, v (X ═ X) denotes the frequency of occurrence of input X in the dataset, and i is the size of the dataset.
Based on the training sample characteristics, the maximum entropy model is used for solving the fault probability S (S) of the insulator<1) If the insulator is a fault insulator, then an insulator fault probability S can be obtained. Sequentially judging whether other insulators have faults or not to obtain corresponding fault probability S 1 ，S 2 ，…，S N . The model with the largest fault probability product is the optimal prediction model, and the insulator fault toilet cleaning model is obtained.
According to the method, the insulator image carrying the insulator label is obtained, wherein the insulator label comprises the insulator fault type and the position of the insulator in a contact network; the method comprises the steps of extracting the characteristics of the insulator image based on a machine vision algorithm to obtain corresponding image characteristics, constructing a training sample based on the image characteristics and a corresponding insulator label, training a support vector machine model by using the training sample to obtain a corresponding insulator fault detection model, and obtaining the insulator fault detection model by combining machine vision and the support vector machine, so that a model with higher precision can be obtained by using smaller data training, and the fault detection of the insulator continued by using the model is more efficient and accurate. Specifically, the maximum entropy model is adopted to inspect the insulator fault detection model, so that the accuracy of the model can be improved, an SVM classifier is adopted in the insulator fault detection model, the required sample data is small, the calculation speed is high, the insulator fault detection model can process the nonlinear problem based on the SVM classifier, and the detection efficiency and accuracy can be improved.
Continuing with the exemplary structure of the device for obtaining an insulator fault detection model 2055 implemented as a software module provided in the embodiment of the present application, in some embodiments, as shown in fig. 2, the software module stored in the device for obtaining an insulator fault detection model 2055 in the memory 205 may include:
an obtaining module 20551, configured to obtain an insulator image carrying the insulator tag; the insulator tag comprises an insulator fault type and the position of the insulator in a contact network;
a feature extraction module 20552, configured to perform feature extraction on the insulator image based on a machine vision algorithm to obtain corresponding image features;
a construction module 20553, configured to construct a training sample based on the image features and the corresponding insulator labels;
the training module 20554 is configured to train a support vector machine model by using the training sample to obtain a corresponding insulator fault detection model;
the insulator fault detection model is used for classifying the image to be detected to obtain the fault type and the insulator position of the insulator in the image to be detected.
In some embodiments, the obtaining 2055 of the insulator fault detection model further includes: the insulator image obtaining module is used for obtaining an initial insulator image; and adding an insulator label to the initial insulator image to obtain an insulator image carrying the insulator label.
In some embodiments, the insulator image obtaining module is further configured to obtain a captured image obtained after the image capturing device captures the contact network area; and preprocessing the shot image to obtain the initial insulator image.
In some embodiments, the insulator image obtaining module is further configured to perform color space conversion processing on the initial insulator image; and/or, performing Gaussian filtering processing on the initial insulator image; and/or performing image enhancement processing on the initial insulator image.
In some embodiments, the training module 20554 is further configured to input the image features into the support vector machine model; classifying based on the image features through the support vector machine model to obtain a prediction classification result, wherein the prediction classification result comprises a prediction fault type and a prediction position; determining an error between the predicted classification result and the insulator label; training the support vector machine model based on the error.
In some embodiments, the training module 20554 is further configured to verify the support vector machine model by using a maximum entropy model and a verification data set, so as to obtain an insulator fault detection model meeting a precision condition.
In some embodiments, the obtaining 2055 of the insulator fault detection model further includes: the fault detection module is used for obtaining an image to be detected; performing feature extraction on the image to be detected based on a machine vision algorithm to obtain corresponding image features to be detected; classifying the characteristics of the image to be detected through the insulator fault detection model to obtain the fault type and the insulator position of the insulator in the image to be detected.
Embodiments of the present application provide a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions, so that the computer device executes the method for obtaining the insulator fault detection model according to the embodiment of the present application.
The embodiment of the application provides a computer-readable storage medium storing executable instructions, wherein the executable instructions are stored, and when being executed by a processor, the executable instructions cause the processor to execute the method for obtaining the insulator fault detection model provided by the embodiment of the application.
In some embodiments, the computer-readable storage medium may be memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash, magnetic surface memory, optical disk, or CD-ROM; or may be various devices including one or any combination of the above memories.
In some embodiments, executable instructions may be written in any form of programming language (including compiled or interpreted languages), in the form of programs, software modules, scripts or code, and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.
By way of example, executable instructions may, but need not, correspond to files in a file system, and may be stored in a portion of a file that holds other programs or data, such as in one or more scripts in a hypertext Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub-programs, or portions of code).
By way of example, executable instructions may be deployed to be executed on one computing device or on multiple computing devices located at one site or distributed across multiple sites and interconnected by a communication 20222.
In summary, the insulator fault detection model capable of efficiently and accurately detecting the insulator fault can be obtained through the embodiment of the application.
The above description is only an example of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, and improvement made within the spirit and scope of the present application are included in the protection scope of the present application.
Claims (10)
1. A method for obtaining an insulator fault detection model is characterized by comprising the following steps:
obtaining an insulator image carrying an insulator label; the insulator tag comprises an insulator fault type and the position of the insulator in a contact network;
performing feature extraction on the insulator image based on a machine vision algorithm to obtain corresponding image features;
constructing a training sample based on the image characteristics and the corresponding insulator label;
training a support vector machine model by using the training sample to obtain a corresponding insulator fault detection model;
the insulator fault detection model is used for classifying the image to be detected to obtain the fault type and the insulator position of the insulator in the image to be detected.
2. The method of claim 1, wherein prior to obtaining the insulator image carrying the insulator label, comprising:
obtaining an initial insulator image;
and adding an insulator label to the initial insulator image to obtain an insulator image carrying the insulator label.
3. The method of claim 2, wherein the obtaining an initial insulator image comprises:
acquiring a shot image obtained after the image shooting equipment shoots the contact network area;
and preprocessing the shot image to obtain the initial insulator image.
4. The method of claim 3, wherein the pre-processing the initial insulator image comprises:
performing color space conversion processing on the initial insulator image;
and/or the presence of a gas in the gas,
performing Gaussian filtering processing on the initial insulator image;
and/or the presence of a gas in the atmosphere,
and carrying out image enhancement processing on the initial insulator image.
5. The method according to claim 3, wherein the training a support vector machine model by using the training samples to obtain a corresponding insulator fault detection model comprises:
inputting the image features into the support vector machine model;
classifying based on the image features through the support vector machine model to obtain a prediction classification result, wherein the prediction classification result comprises a prediction fault type and a prediction position;
determining an error between the predicted classification result and the insulator label;
training the support vector machine model based on the error.
6. The method of claim 5, wherein after training the support vector machine model based on the error, further comprising:
and (3) inspecting the support vector machine model by using a maximum entropy model and a verification data set to obtain an insulator fault detection model meeting the precision condition.
7. The method of claim 1, further comprising:
obtaining an image to be detected;
performing feature extraction on the image to be detected based on a machine vision algorithm to obtain corresponding image features to be detected;
and classifying the characteristics of the image to be detected through the insulator fault detection model to obtain the fault type and the insulator position of the insulator in the image to be detected.
8. An apparatus for obtaining an insulator fault detection model, comprising:
the acquisition module is used for acquiring an insulator image carrying the insulator label; the insulator tag comprises an insulator fault type and the position of the insulator in a contact network;
the characteristic extraction module is used for extracting the characteristics of the insulator images based on a machine vision algorithm to obtain corresponding image characteristics;
the construction module is used for constructing a training sample based on the image characteristics and the corresponding insulator label;
the training module is used for training a support vector machine model by using the training sample to obtain a corresponding insulator fault detection model;
the insulator fault detection model is used for classifying the image to be detected to obtain the fault type and the insulator position of the insulator in the image to be detected.
9. An electronic device, comprising:
a memory for storing executable instructions;
a processor for implementing the method of obtaining an insulator fault detection model according to any one of claims 1 to 7 when executing the executable instructions stored in the memory.
10. A computer-readable storage medium storing executable instructions for implementing the method of obtaining the insulator fault detection model according to any one of claims 1 to 7 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210476401.9A CN114842295A (en) | 2022-04-29 | 2022-04-29 | Method and device for obtaining insulator fault detection model and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210476401.9A CN114842295A (en) | 2022-04-29 | 2022-04-29 | Method and device for obtaining insulator fault detection model and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114842295A true CN114842295A (en) | 2022-08-02 |
Family
ID=82567937
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210476401.9A Pending CN114842295A (en) | 2022-04-29 | 2022-04-29 | Method and device for obtaining insulator fault detection model and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114842295A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117854051A (en) * | 2024-01-11 | 2024-04-09 | 国网山东省电力公司电力科学研究院 | Deep learning-based power transmission line pole insulator image processing method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109801284A (en) * | 2019-01-25 | 2019-05-24 | 华中科技大学 | A kind of high iron catenary insulator breakdown detection method based on deep learning |
| CN112906620A (en) * | 2021-03-09 | 2021-06-04 | 唐山职业技术学院 | Unmanned aerial vehicle-assisted insulator fault detection method and device and electronic equipment |
-
2022
- 2022-04-29 CN CN202210476401.9A patent/CN114842295A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109801284A (en) * | 2019-01-25 | 2019-05-24 | 华中科技大学 | A kind of high iron catenary insulator breakdown detection method based on deep learning |
| CN112906620A (en) * | 2021-03-09 | 2021-06-04 | 唐山职业技术学院 | Unmanned aerial vehicle-assisted insulator fault detection method and device and electronic equipment |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117854051A (en) * | 2024-01-11 | 2024-04-09 | 国网山东省电力公司电力科学研究院 | Deep learning-based power transmission line pole insulator image processing method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ahmad et al. | Object detection through modified YOLO neural network | |
| Tulbure et al. | A review on modern defect detection models using DCNNs–Deep convolutional neural networks | |
| CN109154976B (en) | System and method for training object classifier through machine learning | |
| CN108334848B (en) | Tiny face recognition method based on generation countermeasure network | |
| US9830704B1 (en) | Predicting performance metrics for algorithms | |
| US20180114071A1 (en) | Method for analysing media content | |
| Liu et al. | Data analysis in visual power line inspection: An in-depth review of deep learning for component detection and fault diagnosis | |
| CN109242033A (en) | Wafer defect method for classifying modes and device, storage medium, electronic equipment | |
| Guo et al. | An improved AlexNet for power edge transmission line anomaly detection | |
| CN111598164A (en) | Method and device for identifying attribute of target object, electronic equipment and storage medium | |
| CN110826429A (en) | Scenic spot video-based method and system for automatically monitoring travel emergency | |
| CN111813997A (en) | Intrusion analysis method, device, equipment and storage medium | |
| CN115471216B (en) | Data management method of intelligent laboratory management platform | |
| WO2024060684A1 (en) | Model training method, image processing method, device, and storage medium | |
| Liu et al. | Review of data analysis in vision inspection of power lines with an in-depth discussion of deep learning technology | |
| CN111882034A (en) | Neural network processing and face recognition method, device, equipment and storage medium | |
| CN114943937A (en) | Pedestrian re-identification method and device, storage medium and electronic equipment | |
| CN114842295A (en) | Method and device for obtaining insulator fault detection model and electronic equipment | |
| CN114694130A (en) | Method and device for detecting telegraph poles and pole numbers along railway based on deep learning | |
| Manninen et al. | Multi-stage deep learning networks for automated assessment of electricity transmission infrastructure using fly-by images | |
| CN112348011B (en) | Vehicle damage assessment method and device and storage medium | |
| KR102230559B1 (en) | Method and Apparatus for Creating Labeling Model with Data Programming | |
| CN116580285A (en) | Railway insulator night target identification and detection method | |
| CN116543333A (en) | Target recognition method, training method, device, equipment and medium of power system | |
| Li et al. | Pin bolt state identification using cascaded object detection networks |
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 |