CN111008961B - Transmission line equipment defect detection method and system, equipment and medium thereof - Google Patents
Transmission line equipment defect detection method and system, equipment and medium thereof Download PDFInfo
- Publication number
- CN111008961B CN111008961B CN201911163314.2A CN201911163314A CN111008961B CN 111008961 B CN111008961 B CN 111008961B CN 201911163314 A CN201911163314 A CN 201911163314A CN 111008961 B CN111008961 B CN 111008961B
- Authority
- CN
- China
- Prior art keywords
- image
- transmission line
- line equipment
- power transmission
- defect
- 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.)
- Active
Links
- 230000007547 defect Effects 0.000 title claims abstract description 117
- 230000005540 biological transmission Effects 0.000 title claims abstract description 105
- 238000001514 detection method Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 claims abstract description 48
- 238000004590 computer program Methods 0.000 claims abstract description 14
- 238000007781 pre-processing Methods 0.000 claims abstract description 13
- 238000003066 decision tree Methods 0.000 claims description 26
- 238000004422 calculation algorithm Methods 0.000 claims description 22
- 238000007637 random forest analysis Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 16
- 239000012212 insulator Substances 0.000 claims description 8
- 125000006850 spacer group Chemical group 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 4
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 claims description 3
- 230000008569 process Effects 0.000 description 10
- 230000006870 function Effects 0.000 description 7
- 238000012546 transfer Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000002146 bilateral effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000003373 anti-fouling effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000007246 mechanism Effects 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
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention relates to a method for detecting defects of transmission line equipment, a system, equipment and a medium thereof, wherein the method comprises the following steps: acquiring an image of the power transmission line equipment; classifying the image and determining the defect type of the image; preprocessing the image; and inputting the preprocessed image into a pre-trained recognition model, recognizing the image by the recognition model according to the defect type of the power transmission line equipment in the image, and outputting a defect detection result. The storage medium is a computer-readable storage medium on which a computer program for implementing the power transmission line equipment defect detection method is stored. The equipment comprises a processor and a memory which stores the computer program, and can realize the defect detection method of the power transmission line equipment. By implementing the invention, the defect detection can be carried out on the power transmission line equipment.
Description
Technical Field
The invention relates to the technical field of power transmission lines, in particular to a method and a system for detecting defects of power transmission line equipment, computer equipment and a computer readable storage medium.
Background
In the process of routing inspection of the power transmission line, the main task is to detect the defects of the power transmission line equipment so as to ensure the safe and stable operation of the power grid. The transmission line patrols and examines common line equipment defect and has: insulator fouling and icing, wire clamp loss, spacer abnormality, bolt loss, guy wire rusting and the like.
Disclosure of Invention
The invention aims to provide a method and a system for detecting the defects of power transmission line equipment, computer equipment and a computer readable storage medium, so as to carry out intelligent defect detection on the power transmission line equipment.
In a first aspect, an embodiment of the present invention provides a method for detecting a defect of a power transmission line device, including the following steps:
acquiring an image of the power transmission line equipment;
classifying the image, and determining the type of the defect of the power transmission line equipment in the image;
preprocessing the image;
and inputting the preprocessed image into a pre-trained recognition model, recognizing the power transmission line equipment in the image according to the defect type of the power transmission line equipment in the image by using the recognition model, and outputting a defect detection result.
Preferably, the classifying the image comprises:
and inputting the image into a pre-trained random forest model to obtain the category of the image, wherein the random forest model comprises a plurality of decision trees, each decision tree is used for classifying the image to obtain a classification result, and the random forest model is used for synthesizing the classification results of all the decision trees to obtain the defect type of the power transmission line equipment in the image.
Preferably, the plurality of decision trees are established as follows:
step S1, randomly selecting n samples from the sample set, and randomly selecting K attributes from all defect attributes;
step S2, based on the n samples, selecting the best segmentation attribute in the K attributes to establish a decision tree;
and step S3, returning to step S1 until a decision tree meeting the target quantity is established.
Preferably, the defect types include: insulator fouling and icing, wire clamp loss, spacer anomaly, bolt loss, and/or rust on the pull wire.
Preferably, the preprocessing the image comprises: gray scale distortion, brightness processing, contrast processing, and stitching processing.
Preferably, the recognizing the image by the recognition model according to the defect type of the power transmission line device in the image, and outputting the defect detection result includes:
acquiring an identification algorithm corresponding to the defect type of the power transmission line equipment in the image;
and identifying the image by using the identification algorithm, judging whether the power transmission line equipment in the image has the defect corresponding to the defect type of the power transmission line equipment in the image, and outputting a defect detection result.
In a second aspect, an embodiment of the present invention provides a system for detecting defects of power transmission line equipment, which is used to implement the method for detecting defects of power transmission line equipment in the embodiment of the present invention, and the system includes:
the image acquisition unit is used for acquiring an image of the power transmission line equipment;
the image classification unit is used for classifying the images and determining the defect types of the images;
the image preprocessing unit is used for preprocessing the image;
and the image identification unit is used for inputting the preprocessed image into a pre-trained identification model, identifying the power transmission line equipment in the image according to the defect type of the power transmission line equipment in the image by the identification model, and outputting a defect detection result.
Preferably, the image recognition unit includes:
the algorithm obtaining unit is used for obtaining an identification algorithm corresponding to the defect type of the power transmission line equipment in the image;
and the defect detection unit is used for identifying the image by using the identification algorithm, judging whether the power transmission line equipment in the image has a defect corresponding to the defect type of the power transmission line equipment in the image, and outputting a defect detection result.
In a third aspect, an embodiment of the present invention provides a computer device, including: the defect detection system for the power transmission line equipment is disclosed according to the embodiment of the invention; or, a memory and a processor, where the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, cause the processor to execute the steps of the method for detecting the defect of the power transmission line equipment according to the embodiment of the present invention.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the method for detecting defects of power transmission line equipment according to the embodiment of the present invention.
The embodiment of the invention provides a method and a system for detecting defects of power transmission line equipment, computer equipment and a computer readable storage medium. The embodiment of the invention determines the defect type of the power transmission line equipment in the image by classifying the image; when the defect detection and identification of the power transmission line equipment in the image are carried out, an identification algorithm corresponding to the defect type of the power transmission line equipment in the image is obtained, the power transmission line equipment in the image is identified by using the identification algorithm, and a defect detection result is output. Because the defects of the power transmission line equipment comprise various defects such as insulator fouling and icing, wire clamp loss, spacer abnormality, bolt loss, and/or pull wire rusting, if the same identification algorithm is adopted to detect the defects of the obtained image, the identification algorithm is very complex and needs to consume a large amount of computing resources.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings. Of course, not all of the advantages described above need to be achieved at the same time in the practice of any one product or method of the invention.
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, 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 the drawings without creative efforts.
Fig. 1 is a flowchart of a method for detecting defects of power transmission line equipment according to an embodiment.
FIG. 2 is a diagram of a random forest method according to the first embodiment.
FIG. 3 is a comparison chart before and after image distortion in the first embodiment.
Fig. 4 is a frame diagram of a system for detecting defects of power transmission line equipment according to a second embodiment.
Detailed Description
Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. In the drawings, like reference numbers can indicate functionally identical or similar elements. While the various aspects of the embodiments are presented in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
In addition, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present invention. It will be understood by those skilled in the art that the present invention may be practiced without some of these specific details. In some instances, well known means have not been described in detail so as not to obscure the present invention.
Example one
The embodiment of the invention provides a method for detecting defects of power transmission line equipment, fig. 1 is a flow chart of the method for detecting the defects of the power transmission line equipment, and referring to fig. 1, the method of the embodiment comprises the following steps of S101-S104:
s101, acquiring an image of the power transmission line equipment;
specifically, the power transmission line equipment comprises equipment components such as power transmission lines, insulators, wire clamps, spacers and bolts, and an image of the power transmission line equipment obtained by shooting through a camera on site may comprise one or more of the equipment components.
S102, classifying the image, and determining the type of the defect of the power transmission line equipment in the image;
specifically, the image is input into a pre-trained random forest model (NFA model) to obtain the category of the image, the random forest model comprises a plurality of decision trees, each decision tree is used for classifying the image to obtain a classification result, and the random forest model is used for obtaining the defect type of the power transmission line equipment in the image by integrating the classification results of all the decision trees.
Because the types of the fine defects of the power transmission line equipment are more, the classification difficulty is higher when the power transmission line equipment is detected. Therefore, aiming at the tiny defects of the power transmission line equipment, a machine learning-based NFA model is established by starting from information such as real-time monitoring data, operation data and historical fault maintenance times of the equipment, so that the classification of the tiny defects of the power transmission line is realized. The establishment of the NFA model is to enable the detection rule to be visualized, avoid errors caused by a linear regression method, enable the established model to have interpretability, and use a decision tree mode of a random forest for modeling. In order to reduce parameters needing to be adjusted, efficiently process mass sample data and classify the fine defects of the power transmission line, so that the model has stronger adaptability to detection samples, linear regression is abandoned and random forest regression modeling is adopted on the basis of the NFA model. The random forest method is shown in fig. 2.
The basic principle of the random forest method is as follows: firstly, selecting four samples of a, b, c and d in original data by utilizing autonomous sampling, establishing a transfer relation between certain two selected samples, wherein the transfer relation can generate a probability vector with an interval of [0,1] for a certain sample. The NFA model of the fine defect of the electric transmission line equipment is composed of transfer relations among samples, and if there are N samples, there are { F1(X), F2(X), … …, fn (X) }, where X ═ X1, X2, … …, xN } is a feature vector of the N-direction dimension of the fine defect.
In this embodiment, the NFA model is used in classification of fine defects of devices, and a prediction result is called for modeling for each randomly selected sample, where one sample corresponds to one decision tree, and all decision trees form a random forest. The NFA defines the process of model establishment, and for a randomly-extracted sample, when detecting a fine defect in the sample, firstly, a probability vector capable of determining the transfer relationship is selected, then, a decision tree is obtained from the distribution of the transfer relationship, and the process is continuously repeated until each decision tree in a random forest is extracted. The construction of the NFA model effectively solves the classification of the fine defects of the power transmission line equipment and provides a basis for the next detection.
Wherein the defect types include: insulator fouling and icing, wire clamp loss, spacer anomaly, bolt loss, and/or rust on the pull wire.
Wherein the pre-processing the image comprises: gray scale distortion, brightness processing, contrast processing, and stitching processing.
Wherein the establishment process of the decision trees is as follows:
step S1, randomly selecting n samples from the sample set by Bootstrap, and randomly selecting K attributes from all defect attributes;
step S2, based on the n samples, selecting the best segmentation attribute in the K attributes as a node to establish a CART decision tree; the CART decision tree is a classifier, and of course, the decision tree may be other types of classifiers, such as SVM and Logistics;
and S3, returning to S1, and repeating the steps S1-S2 until a decision tree meeting the target quantity is established.
Finally, a plurality of CART decision trees form a random forest, which type the data belong to is determined according to voting results, and the voting mechanism is provided with a vote rejection control system, a minority obedience majority and a weighted majority.
Step S103, preprocessing the image;
in the process of shooting and transmitting images by the transmission line inspection equipment, the transmission line inspection equipment is interfered by irregular external signals, so that gray level distortion or Gaussian noise and the like appear in the images, and the observation and judgment of people on the fine defects of the equipment are influenced. The generated distortion and noise mainly have the following two effects on the fine defect detection of the power transmission line equipment: (1) distortion and noise are generated in an image, so that the definition of an actual condition area of a target image to be detected is reduced, the recognition system is caused to understand that the image is not reliable, a normal template before the distortion and the noise are generated is updated by default, and the whole shot target is lost in a serious condition;
(2) distortion and noise can cause the approximation degree of an actual area to be lower than that of a simulation related area, so that errors occur when a tracking system tracks a target, and the tracking precision is reduced or the tracked target is lost.
In the working process of equipment detection, the influence of gray level distortion and noise of most image pixels is relatively slow and is difficult to perceive at the early stage. The default target to be measured and the background gray scale are both unique, so that the picture pixels can be simplified into a 4 × 4 matrix, each small square in the matrix represents a pixel, which is equivalent to the average brightness of the real target area 1/16 represented. Assuming that the distortion type in the pixel is single and the distortion amplitude is large, for the convenience of research, the pixel with gray scale distortion is regarded as the target, and the remaining undistorted pixels are regarded as the background, and the specific change is shown in fig. 3.
The application of picture identification in power transmission line inspection is combined, and according to the influence of the interference factors, some processing needs to be carried out on the collected audio-video images:
and (3) brightness processing: the brightness of the image is first adjusted, which gives the person visually different brightness in different situations for a certain object brightness. When the captured video image is too bright or too dark, the difficulty of video image recognition is increased. It is necessary to adjust the brightness. The method for adjusting the brightness is HSL (HSV) color space adjustment, and the method is applied to external shooting and is the most intuitive and efficient method, because a natural L component expresses the brightness in the HSL color space, and the L component can be directly adjusted. However, it should be noted that the video images are displayed by a computer, and the computer screen can adjust most of the video images in the RGB color space, so that all the video images need to be converted into the HSL color space after being received, which is convenient for further processing of the images.
Contrast processing: in a poor weather environment, the contrast of the video image is poor. In order to remove the influence of haze or rain and snow shielding the equipment to be tested in the video image, the contrast of the image needs to be properly enlarged or reduced under the condition of unchanged brightness, and the adjustment formula is as follows:
lout＝laverage+(ln-laverage)(1+percent)
in the above formula, /)nRepresenting the brightness value, l, of a pixel in the original pictureaverageRepresenting the average brightness value, l, of the entire video imageoutRepresenting the brightness value of the pixel point in the adjusted picture, and the percentage representing the adjustment range of the brightness value of the video image, wherein the adjustment range is [ -1,1]. After the adjustment, the contrast of the audio-video image is further processed by utilizing the characteristics of haze and rain and snow for the detection of the audio-video image. The Gaussian filter function is the basis of bilateral filtering, and because the influence of the pixels at the edge of the Gaussian filter function on the picture is small, the pixels at the edge can be better protected when haze, rain and snow are removed. In rainy and snowy weather, the rain lines are brighter in the video images, but due to the fact that time domain changes rapidly, rain drops need to be removed by a bilateral filter in time domain pixels. For video, the pixel values of rain and snow need to be described in terms of physical characteristics, and a frequency domain is introduced to filter haze, rain and snow.
Image splicing: since the camera resolution of the power line detection apparatus is limited, the resolution of the image is lower when the area of the scene to be photographed is larger. Therefore, when a scene with a large area needs to be shot, the resolution of the image cannot be improved, so that the scene needs to be divided, and after the scene is shot respectively, the images are spliced together to meet the resolution requirement in the actual detection work. According to the matching standard of similar identification, the method of image splicing matching selects NFA model-based matching, the method does not need to directly use image pixels, but derives pixel values from image features, then effective features are selected by using the model as reference, and corresponding features of image superposition tend to be superposed, so that the image processing is completed.
And S104, inputting the preprocessed image into a pre-trained recognition model, recognizing the power transmission line equipment in the image according to the defect type of the power transmission line equipment in the image by using the recognition model, and outputting a defect detection result.
Wherein, step S104 includes:
step S201, obtaining an identification algorithm corresponding to the defect type of the power transmission line equipment in the image;
step S202, identifying the image by using the identification algorithm, judging whether the power transmission line equipment in the image has a defect corresponding to the defect type of the power transmission line equipment in the image, and outputting a defect detection result.
Specifically, image recognition of the transmission line is to find the transmission line region in an image photographed by a computer. The shooting of a transmission line is often accompanied by the influence of complex weather, therefore, target extraction is very difficult in many times, and the image recognition problem must be solved by using the strong applicability of an image processing algorithm, for example, a statistical-based method has the characteristic of strong applicability, the Adaboost algorithm can have a good recognition effect, a training set containing positive and negative samples and a classification number are calibrated, the weight of all training samples is 1/N, N represents the number of the samples, and for each sample, the weight error function epsilon of each sample is enabled to be equal to the weight error function epsilonmAnd (3) minimizing:
in the above formula, m is 1, 2mAs weak classifiers, omeganIs the weight of the weak classifier, I is the probability, the speaking weight alpha of the weak classifier is calculated by the above formulam：
Obtaining the final strong classifier Ym(X):
The Adaboost algorithm is utilized to obtain the strong classifier by combining the weak classifiers, the strong classifier is not easily interfered by signals in the process, the problems of Gaussian noise and gray distortion are solved, and the detection equipment of the power transmission line has a better image recognition effect.
Specifically, the insulator anti-fouling and anti-icing clamp aims at the defects of insulator fouling and icing, wire clamp missing, spacer abnormity, bolt loss, pull wire rusting and the like. In the training process, aiming at each type, a plurality of positive samples and negative samples are collected, wherein the positive samples are normal equipment images, the negative samples are defect equipment images, and classification is carried out by extracting the characteristics of the images and according to the characteristics of the images. Thus, a classification algorithm for each defect type can be obtained.
Preferably, the present embodiment classifies the images by extracting gradient information of features of the images, and after training, a difference of gradient information between a normal device image and a defective device image can be obtained, and accordingly, classification and identification of device defects are performed, wherein a template of gradient calculation is shown in the following formula:
for the established two-dimensional image f (x, y), in this embodiment, the gradient of the moving pixel point (x, y) is calculated, and is specifically expressed by a vector equation system:
in the above formula, fxRepresents the gradient on the x-axis, fyThe gradient on the y-axis is represented, m represents the gradient magnitude, and θ represents the gradient inclination angle. Most of line elements extracted by the traditional calculation method of phase grouping are greatly influenced by distortion and noise, and the gradient positioning precision is not accurate in most cases, so that the corresponding phase is deviated, and the segmentation effect is influenced. To address this deficiency, gradients have been developedThe traditional calculation process is that f isxAnd fyThe gradient direction is calculated by the gray difference, and when noise exists, the value of the gray difference deviates from the true value, so that the result is not ideal. Therefore, in this embodiment, a method for detecting an image edge by using a Sobel operator is introduced to obtain a gradient, and a gradient range is calculated to be [0 °, 360 ° ]]. Although the calculation amount is larger than that of the traditional method, the detection result is more accurate.
Example two
An embodiment of the present invention provides a system for detecting defects of power transmission line equipment, which is used to implement the method for detecting defects of power transmission line equipment described in the embodiment one, and fig. 4 is a frame diagram of the system described in this embodiment, referring to fig. 4, where the system includes:
the image acquisition unit 1 is used for acquiring an image of the power transmission line equipment;
the image classification unit 2 is used for classifying the images and determining the defect types of the images;
an image preprocessing unit 3 for preprocessing the image;
and the image identification unit 4 is used for inputting the preprocessed image into a pre-trained identification model, identifying the power transmission line equipment in the image according to the defect type of the power transmission line equipment in the image by the identification model, and outputting a defect detection result.
Preferably, the image recognition unit 4 includes:
the algorithm obtaining unit 41 is configured to obtain an identification algorithm corresponding to a defect type to which the power transmission line device belongs in the image;
and the defect detection unit 42 is configured to identify the image by using the identification algorithm, determine whether the power transmission line device in the image has a defect corresponding to the defect type of the power transmission line device in the image, and output a defect detection result.
The above-described system embodiments are merely illustrative, and 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 modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the embodiment of the system provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, and may be specifically implemented as one or more communication buses or signal lines. One of ordinary skill in the art can understand and implement it without inventive effort.
It should be noted that the system according to the second embodiment corresponds to the method according to the first embodiment, and therefore, a part of the system according to the second embodiment that is not described in detail can be obtained by referring to the content of the method according to the first embodiment, and is not described again here.
In addition, if the system for detecting defects of power transmission line equipment according to the second embodiment is implemented in the form of a software functional unit and sold or used as an independent product, the system can be stored in a computer-readable storage medium.
EXAMPLE III
An embodiment of the present invention provides a computer device, including: the defect detection system of the power transmission line equipment is provided according to the third embodiment of the invention; or, a memory and a processor, where the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, cause the processor to execute the steps of the method for detecting the defect of the power transmission line equipment according to the embodiment of the present invention.
Of course, the computer device may also have components such as a wired or wireless network interface, a keyboard, and an input/output interface, so as to perform input/output, and the computer device may also include other components for implementing the functions of the device, which are not described herein again.
Illustratively, the computer program may be divided into one or more units, which are stored in the memory and executed by the processor to accomplish the present invention. The one or more units may be a series of computer program instruction segments capable of performing certain functions, which are used to describe the execution of the computer program in the computer device.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, etc. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is the control center for the computer device and connects the various parts of the overall computer device using various interfaces and lines.
The memory may be used for storing the computer program and/or unit, and the processor may implement various functions of the computer device by executing or executing the computer program and/or unit stored in the memory and calling data stored in the memory. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
Example four
The fourth embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the method for detecting defects of power transmission line equipment according to the first embodiment of the present invention.
Specifically, the computer-readable storage medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like.
Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (7)
1. A method for detecting defects of transmission line equipment is characterized by comprising the following steps:
acquiring an image of the power transmission line equipment;
classifying the image, and determining the type of the defect of the power transmission line equipment in the image; wherein the classifying the image comprises: inputting the image into a pre-trained random forest model to obtain the category of the image, wherein the random forest model comprises a plurality of decision trees, each decision tree is used for classifying the image to obtain a classification result, and the random forest model is used for integrating the classification results of all the decision trees to obtain the defect type of the power transmission line equipment in the image;
preprocessing the image;
inputting the preprocessed image into a pre-trained recognition model, recognizing the power transmission line equipment in the image according to the defect type of the power transmission line equipment in the image by the recognition model, and outputting a defect detection result; the method comprises the steps of obtaining an identification algorithm corresponding to the type of the defect to which the power transmission line equipment belongs in an image, identifying the image by using the identification algorithm, judging whether the power transmission line equipment in the image has the defect corresponding to the type of the defect to which the power transmission line equipment belongs in the image, and outputting a defect detection result.
2. The method of claim 1, wherein the plurality of decision trees are established as follows:
step S1, randomly selecting n samples from the sample set, and randomly selecting K attributes from all defect attributes;
step S2, based on the n samples, selecting the best segmentation attribute in the K attributes to establish a decision tree;
and step S3, returning to step S1 until a decision tree meeting the target quantity is established.
3. The method for detecting the defect of the transmission line equipment according to claim 1, wherein the defect types include: insulator fouling and icing, wire clamp loss, spacer anomaly, bolt loss, and/or rust on the pull wire.
4. The method for detecting defects of transmission line equipment according to claim 1, wherein the preprocessing the image comprises: gray scale distortion, brightness processing, contrast processing, and stitching processing.
5. A system for detecting defects of transmission line equipment, which is used for realizing the method for detecting the defects of the transmission line equipment as claimed in any one of claims 1 to 4, and is characterized by comprising the following components:
the image acquisition unit is used for acquiring an image of the power transmission line equipment;
the image classification unit is used for classifying the images and determining the defect types of the images;
the image preprocessing unit is used for preprocessing the image;
the image recognition unit is used for inputting the preprocessed image into a recognition model which is trained in advance, recognizing the power transmission line equipment in the image according to the defect type of the power transmission line equipment in the image, and outputting a defect detection result;
wherein the image recognition unit includes:
the algorithm obtaining unit is used for obtaining an identification algorithm corresponding to the defect type of the power transmission line equipment in the image;
and the defect detection unit is used for identifying the image by using the identification algorithm, judging whether the power transmission line equipment in the image has a defect corresponding to the defect type of the power transmission line equipment in the image, and outputting a defect detection result.
6. A computer device, comprising: the transmission line equipment defect detection system of claim 5; or a memory and a processor, wherein the memory has stored therein computer readable instructions, which when executed by the processor, cause the processor to perform the steps of the method for detecting defects in electric line equipment according to any one of claims 1 to 4.
7. A computer-readable storage medium having stored thereon a computer program, characterized in that: the computer program, when being executed by a processor, implements the steps of the method for detecting defects in power transmission line equipment according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911163314.2A CN111008961B (en) | 2019-11-25 | 2019-11-25 | Transmission line equipment defect detection method and system, equipment and medium thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911163314.2A CN111008961B (en) | 2019-11-25 | 2019-11-25 | Transmission line equipment defect detection method and system, equipment and medium thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111008961A CN111008961A (en) | 2020-04-14 |
| CN111008961B true CN111008961B (en) | 2021-10-19 |
Family
ID=70113084
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911163314.2A Active CN111008961B (en) | 2019-11-25 | 2019-11-25 | Transmission line equipment defect detection method and system, equipment and medium thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111008961B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111784645B (en) * | 2020-06-15 | 2023-08-22 | 北京科技大学 | Filling pipeline crack detection method |
| CN111862065B (en) * | 2020-07-28 | 2022-08-26 | 国电南瑞科技股份有限公司 | Power transmission line diagnosis method and system based on multitask deep convolutional neural network |
| CN112070246A (en) * | 2020-08-26 | 2020-12-11 | 上海洪朴信息科技有限公司 | Photovoltaic product defect detection algorithm deployment system |
| CN112767364B (en) * | 2021-01-22 | 2022-06-17 | 三峡大学 | Image detection system for gate blade surface corrosion and corrosion area rapid measuring and calculating method |
| CN113177544A (en) * | 2021-04-27 | 2021-07-27 | 大连工业大学 | Method for detecting damage and blood stain residue in tilapia processing process |
| CN113192065A (en) * | 2021-05-28 | 2021-07-30 | 广东电网有限责任公司 | Processing method of power transmission line image, portable equipment and user terminal |
| CN114359285B (en) * | 2022-03-18 | 2022-07-29 | 南方电网数字电网研究院有限公司 | Power grid defect detection method and device based on visual context constraint learning |
| CN117726623B (en) * | 2024-02-07 | 2024-05-24 | 深圳新视智科技术有限公司 | Binary tree line detection method and device and computer equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109118482A (en) * | 2018-08-07 | 2019-01-01 | 腾讯科技（深圳）有限公司 | A kind of panel defect analysis method, device and storage medium |
| US10303823B2 (en) * | 2017-03-30 | 2019-05-28 | I-Shou University | Defect detection method for 3D chip and system using the same |
| CN109859177A (en) * | 2019-01-17 | 2019-06-07 | 航天新长征大道科技有限公司 | Industrial x-ray image assessment method and device based on deep learning |
| CN109902584A (en) * | 2019-01-28 | 2019-06-18 | 深圳大学 | A kind of recognition methods, device, equipment and the storage medium of mask defect |
| CN109916906A (en) * | 2018-10-11 | 2019-06-21 | 乐人株式会社 | Defect detecting device and method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108471114B (en) * | 2018-04-23 | 2020-05-12 | 广州供电局有限公司 | Power transmission line state evaluation method and device, computer equipment and storage medium |
-
2019
- 2019-11-25 CN CN201911163314.2A patent/CN111008961B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10303823B2 (en) * | 2017-03-30 | 2019-05-28 | I-Shou University | Defect detection method for 3D chip and system using the same |
| CN109118482A (en) * | 2018-08-07 | 2019-01-01 | 腾讯科技（深圳）有限公司 | A kind of panel defect analysis method, device and storage medium |
| CN109916906A (en) * | 2018-10-11 | 2019-06-21 | 乐人株式会社 | Defect detecting device and method |
| CN109859177A (en) * | 2019-01-17 | 2019-06-07 | 航天新长征大道科技有限公司 | Industrial x-ray image assessment method and device based on deep learning |
| CN109902584A (en) * | 2019-01-28 | 2019-06-18 | 深圳大学 | A kind of recognition methods, device, equipment and the storage medium of mask defect |
Non-Patent Citations (1)
| Title |
|---|
| 随机森林在板材表面缺陷分类中的应用;胡峻峰 等;《东北林业大学学报》;20150831;第43卷(第8期);第86-90段 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111008961A (en) | 2020-04-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111008961B (en) | Transmission line equipment defect detection method and system, equipment and medium thereof | |
| US20220309637A1 (en) | Electronic substrate defect detection | |
| CN107507173B (en) | No-reference definition evaluation method and system for full-slice image | |
| CN109241985B (en) | Image identification method and device | |
| CN108489996B (en) | Insulator defect detection method and system and terminal equipment | |
| CN110033431B (en) | Non-contact detection device and detection method for detecting corrosion area on surface of steel bridge | |
| CN107679495B (en) | Detection method for movable engineering vehicles around power transmission line | |
| CN110443212B (en) | Positive sample acquisition method, device, equipment and storage medium for target detection | |
| CN109448009A (en) | Infrared Image Processing Method and device for transmission line faultlocating | |
| CN111767915A (en) | License plate detection method, device, equipment and storage medium | |
| CN106960196B (en) | Industrial video small number recognition method based on template matching and SVM | |
| CN105095835A (en) | Pedestrian detection method and system | |
| CN115830004A (en) | Surface defect detection method, device, computer equipment and storage medium | |
| CN105740844A (en) | Insulator cracking fault detection method based on image identification technology | |
| CN113673515A (en) | Computer vision target detection algorithm | |
| CN112116568A (en) | Image quality evaluation method and device and storage medium | |
| CN111680704A (en) | Automatic and rapid extraction method and device for newly-increased human active plaque of ocean red line | |
| CN112288682A (en) | Electric power equipment defect positioning method based on image registration | |
| CN115115950A (en) | Unmanned aerial vehicle image duplicate checking method based on image histogram features | |
| CN110569716A (en) | Goods shelf image copying detection method | |
| CN114529906A (en) | Method and system for detecting abnormity of digital instrument of power transmission equipment based on character recognition | |
| CN114596242A (en) | Defect detection method, defect detection device, electronic equipment and computer readable storage medium | |
| CN115273013B (en) | Lane line detection method, system, computer and readable storage medium | |
| CN116309270A (en) | Binocular image-based transmission line typical defect identification method | |
| CN117011216A (en) | Defect detection method and device, electronic equipment and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |