CN113538371B - Power distribution network overhead line icing thickness monitoring method for improving K-means clustering - Google Patents
Power distribution network overhead line icing thickness monitoring method for improving K-means clustering Download PDFInfo
- Publication number
- CN113538371B CN113538371B CN202110796620.0A CN202110796620A CN113538371B CN 113538371 B CN113538371 B CN 113538371B CN 202110796620 A CN202110796620 A CN 202110796620A CN 113538371 B CN113538371 B CN 113538371B
- Authority
- CN
- China
- Prior art keywords
- image
- distribution network
- straight line
- power distribution
- overhead line
- 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
- 238000009826 distribution Methods 0.000 title claims abstract description 53
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000012544 monitoring process Methods 0.000 title claims abstract description 41
- 238000003064 k means clustering Methods 0.000 title claims abstract description 31
- 239000011248 coating agent Substances 0.000 claims abstract description 24
- 238000000576 coating method Methods 0.000 claims abstract description 24
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 238000010801 machine learning Methods 0.000 claims abstract description 4
- 238000012545 processing Methods 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 7
- 230000000877 morphologic effect Effects 0.000 claims description 7
- 239000004020 conductor Substances 0.000 claims description 5
- 238000004380 ashing Methods 0.000 claims description 4
- 239000000203 mixture Substances 0.000 claims description 2
- 239000002994 raw material Substances 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005315 distribution function Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 241000519995 Stachys sylvatica Species 0.000 description 1
- 238000002679 ablation Methods 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 1
- 229910052782 aluminium Inorganic materials 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010924 continuous production Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000008014 freezing Effects 0.000 description 1
- 238000007710 freezing Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011056 performance test Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000008234 soft water Substances 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Water Supply & Treatment (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Public Health (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a power distribution network overhead line icing thickness monitoring method for improving K-means clustering, which comprises the steps of acquiring a power distribution network overhead line image by using a monocular camera; preprocessing the power distribution network overhead line image according to a machine vision strategy; conducting wire edge positioning on the preprocessed power distribution network overhead line image by applying a machine vision and machine learning algorithm; and calculating the ice coating thickness of the overhead line and outputting a monitoring result. The method can accurately position the position of the overhead line, judge the icing state of the overhead line on the basis of the position, has high identification precision, meets the actual engineering requirements, can help the electric power department to find potential ice and snow disaster risks in time, and has higher practical value.
Description
Technical Field
The invention relates to the technical field of key equipment management and operation maintenance of a power distribution network, in particular to a power distribution network overhead line icing thickness monitoring method improved in K-means clustering.
Background
With the development of economy, the power grid structure of a power system is stronger and stronger, the living electricity generated by people is guaranteed, and the requirement of people on the quality of electric energy is higher and higher. At the same time, the power grid is also subjected to attacks and troubles from various natural disasters, especially the whole power distribution network. Among the natural disasters, ice disasters are particularly common and widespread, and are one of the most common and threatening disasters in power distribution networks and large power grids. After ice disasters occur, the distribution network has ice flashover when the ice disasters occur, and has the problems of disconnection, pole falling and the like when the ice flashover occurs, and large-area power failure can be caused more seriously, so that huge economic loss and adverse social influence are caused. Therefore, monitoring of ice coating thickness of overhead lines of a power distribution network is particularly important.
In the related research of the monitoring of the icing thickness of the overhead line of the power distribution network, the Huangxinbo et al provides an overhead line icing thickness monitoring method based on the fusion of a genetic algorithm and fuzzy logic. However, the model may cause over-learning and local minimum problems, the ice thickness determination precision is not high, and a large amount of historical data needs to be acquired from a plurality of ice coating monitoring terminals, so that the application is complicated. King and peton et al propose an overhead line icing thickness monitoring method based on an image method, which includes acquiring line icing images through a camera mounted on a base tower, detecting line icing edges by utilizing wavelet transformation, and calculating line icing thickness by comparing equivalent lines before and after icing. However, in the application process of the method, if the situation of the ice coating is repeated, the situation that the camera lens cannot acquire the image due to the ice coating shielding may occur.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
The present invention has been made in view of the above-mentioned conventional problems.
Therefore, the invention provides the power distribution network overhead line icing thickness monitoring method for improving K-means clustering, and the problem that the icing thickness of the power distribution network overhead line cannot be accurately identified in a severe environment can be solved.
In order to solve the technical problems, the invention provides the following technical scheme: the method for monitoring the icing thickness of the empty line of the distribution network frame by improving K-means clustering is characterized by comprising the following steps of: acquiring an empty line image of a power distribution network frame by using a monocular camera; preprocessing the power distribution network overhead line image according to a machine vision strategy; conducting wire edge positioning is conducted on the preprocessed power distribution network overhead line image by applying a machine vision and machine learning algorithm; and calculating the ice coating thickness of the overhead line and outputting a monitoring result.
As an optimal scheme of the method for monitoring the icing thickness of the overhead line of the power distribution network by improving K-means clustering, the method comprises the following steps: the preprocessing comprises image filtering, morphological operation, ashing degree, contrast enhancement and image denoising.
As an optimal scheme of the method for monitoring the icing thickness of the overhead line of the power distribution network by improving K-means clustering, the method comprises the following steps: the positioning of the edge of the lead comprises the steps of roughly determining the edge position of the lead through a straight line segment of the edge of the lead obtained by straight line segment detection; dividing the straight line segments of the edge of the conducting wire by using an improved K-means clustering algorithm; and obtaining a smooth wire edge by means of fitting.
As an optimal scheme of the method for monitoring the icing thickness of the overhead line of the power distribution network by improving K-means clustering, the method comprises the following steps: calculating the ice coating thickness of the overhead line, namely judging the ice coating state of the overhead line according to the positioned conductor; the widths of the wires before and after icing are respectively countedCalculating the width values of the wires before and after icing, and taking the difference value of the width values of the wires before and after icing as a criterion; calculating the real-time width W of the wire1Then subtracting the diameter W of the ice-free wire2I.e. the current ice layer thickness.
As an optimal scheme of the method for monitoring the icing thickness of the overhead line of the power distribution network by improving K-means clustering, the method comprises the following steps: the monitoring results comprise the icing state, the ice layer thickness, errors and time-consuming duration.
As an optimal scheme of the method for monitoring the icing thickness of the overhead line of the power distribution network by improving K-means clustering, the method comprises the following steps: the linear segment detection comprises the steps of compressing the length and the width of the preprocessed image to 80% of the original size so as to weaken the sawtooth effect when the pixel points form the linear segment; respectively carrying out convolution operation on the reduced image and a convolution kernel to obtain gradients G in the x direction and the y directionx、GyAnd the edge points of the image are searched after the gradient magnitude is calculated, as follows,
wherein G is the edge point of the image which is searched after the gradient amplitude value starts, Gx、GyThe gradient in the x direction and the gradient in the y direction respectively.
As an optimal scheme of the method for monitoring the icing thickness of the overhead line of the power distribution network by improving K-means clustering, the method comprises the following steps: dividing the straight line segments at the edge of the wire by using an improved K-means clustering algorithm, wherein the method comprises the steps of taking a reference line in an image and calculating the distance from each straight line segment to the reference line; judging the edge according to the distance; and if the slopes of the straight line segments are different and the straight line segments are not parallel to the datum line, the distance between the straight line segments and the datum line cannot be calculated, and the straight line segments are processed.
As an optimal scheme of the method for monitoring the icing thickness of the overhead line of the power distribution network by improving K-means clustering, the method comprises the following steps: the processing comprises defining the slope and intercept of n straight line segments as k respectively1,k2,…,knAnd b1,b2,…,bnDividing the lead wires into m types, wherein m is 2 times of the number of the lead wires; arbitrarily taking a reference point in the image, the coordinate is (x)0,y0)，0＜x0＜h，0＜y0< w, where h, w are the image height and width, respectively.
As an optimal scheme of the method for monitoring the icing thickness of the overhead line of the power distribution network by improving K-means clustering, the method comprises the following steps: also included is an over reference point (x)0,y0) Are respectively represented by k1,k2,…,knTaking the slope as a reference line, and calculating the distance d from each reference line to the corresponding straight line segmenti(i-1, 2, …, n), as follows,
with (d)i,ki) Denotes the ith straight line segment, will (d)i,ki) And (i-1, 2, …, n) are all substituted into the K-means clustering algorithm to be classified into m types, so that the classification of all straight line segments in the image is completed.
The invention has the beneficial effects that: the method for monitoring the icing thickness of the power distribution network frame empty line based on the improved K-means clustering can position the overhead line conductor in the image, solve the width of the conductor at the moment on the basis and obtain the thickness of an ice layer by combining a reference value; the current icing state of the overhead line can be judged according to the comprehensive analysis of the ice layer thickness and the historical icing data; under the experimental environment, the error is not more than +/-0.1 cm, and the method has good precision.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts. Wherein:
fig. 1 is a schematic flow chart of a method for monitoring icing thickness of an overhead line of a power distribution network based on improved K-means clustering according to an embodiment of the present invention;
fig. 2 is a schematic diagram of convolution kernels in x and y directions of the method for monitoring the icing thickness of the overhead line of the power distribution network based on the improved K-means clustering according to the embodiment of the invention;
fig. 3 is a schematic diagram illustrating comparison between an ice-coated line and an ice-uncoated line in the method for monitoring ice-coating thickness of an overhead line of a power distribution network based on improved K-means clustering according to an embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, specific embodiments accompanied with figures are described in detail below, and it is apparent that the described embodiments are a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present invention, shall fall within the protection scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described and will be readily apparent to those of ordinary skill in the art without departing from the spirit of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
Furthermore, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
The present invention will be described in detail with reference to the drawings, wherein the cross-sectional views illustrating the structure of the device are not enlarged partially in general scale for convenience of illustration, and the drawings are only exemplary and should not be construed as limiting the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in the actual fabrication.
Meanwhile, in the description of the present invention, it should be noted that the terms "upper, lower, inner and outer" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation and operate, and thus, cannot be construed as limiting the present invention. Furthermore, the terms first, second, or third are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected," and "connected" are to be construed broadly and include, for example: can be fixedly connected, detachably connected or integrally connected; they may be mechanically, electrically, or directly connected, or indirectly connected through intervening media, or may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example 1
For a long time, the key points of the anti-icing and anti-icing work of the line are mainly concentrated on the main network power transmission line, the anti-icing work of the power distribution network is weakened, the safe and stable operation of the power distribution network directly relates to the power utilization reliability and the personal interests of people in daily life, and therefore the attention to the anti-icing and anti-icing work of the power distribution network is necessarily strengthened.
In order to comprehensively improve the ice resistance of a distribution network and ensure the power supply reliability of the distribution network in the ice season, the embodiment provides the power distribution network overhead line ice coating thickness monitoring method based on improved K-means clustering.
Referring to fig. 1,2 and 3, a first embodiment of the present invention provides a method for monitoring ice thickness of an overhead line of a power distribution network with improved K-means clustering, which is characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
s1: and acquiring the image of the overhead line of the power distribution network by using a monocular camera. Wherein, it is required to be noted that:
acquiring image data of the overhead line by adopting a monocular camera, inputting the image data into a portable computer for processing, and measuring the width of the overhead line by using a vernier caliper;
considering that the steel-cored aluminum strand is heavy and needs a special tool for processing, a galvanized pipe with similar shape and color is used for simulating an actual overhead line;
the ice-coated overhead line is made by putting a galvanized pipe into a soft water pipe filled with water, freezing in a cold storage, and simulating a background environment with a single-color cloth.
S2: and preprocessing the overhead line image of the power distribution network according to a machine vision strategy. This step is to be explained, and the pretreatment includes:
image filtering, morphological operation, ashing degree, contrast enhancement and image denoising;
image filtering: the main noise types in the image are Gaussian noise and pulse noise, and the image is removed after convolution by a median filtering kernel in the following formula, so that the denoising work is preliminarily completed.
Wherein x and y are respectively the horizontal and vertical coordinates of the pixel points; σ is the standard deviation of the Gaussian distribution; p (x, y) is the value of the pixel after convolution.
P(x,y)＝median[f(x-1,y-1),f(x,y-1),f(x+1,y-1),f(x-1,y),
f(x,y),f(x+1,y),f(x-1,y+1),f(x,y+1),f(x+1,y+1)]
Wherein f is the pixel value of the pixel point adjacent to the point to be measured.
Morphological operation: after the filtering and preliminary denoising, part of noise existing in the form of white spots or black holes in the image is removed through a morphological opening operation and a morphological closing operation respectively as follows:
wherein, P is an image to be processed; q is a structural element;
performing corrosion operation;
for the expansion operation.
Ashing degree treatment: because overhead line icing thickness detection mainly detects wire upper and lower profile edge, does not relate to the colour problem, carries out grey scale processing with the image of gathering, improves the operation rate of image processing as follows:
Gray(x,y)＝0.3R(x,y)+0.59G(x,y)+0.11B(x,y)
wherein, Gray (x, y) is a grayed value of a pixel point in the image at the point (x, y); r (x, y), B (x, y) and G (x, y) are pixel values of pixel points in red, blue and green channels respectively.
Contrast enhancement: in order to enlarge the difference between the overhead line and the background and enable the edge of the wire to be easier to detect, linear expansion is carried out on the gray level image by adopting a linear function, and contrast enhancement processing is carried out, wherein the contrast enhancement processing comprises the following steps:
wherein f (x, y) is a gray distribution function in the gray image; [ a, b ] is the pixel gray scale distribution range in the gray scale image; g (x, y) is a gray distribution function of the image after gray conversion.
Denoising the image by adopting an improved wavelet threshold method: the image is blurred due to various noise interferences and influences in the generation and transmission processes, although the noise interferences and influences can be effectively reduced through image filtering and morphological operations, the noise still exists at the edge of the processed partial image, and the ice coating thickness monitoring of the overhead line of the distribution network needs to be based on a clear line boundary contour, so that the processing is performed by adopting an improved wavelet threshold denoising method, and the specific steps are as follows:
(1) weighting two estimation methods of a hard threshold and a soft threshold to obtain the following thresholds:
wherein, Wj,kIs a wavelet coefficient; λ is wavelet threshold; the weight value a is [0,1 ]]Any constant number of (1).
(2) Will be [0,1 ]]N is equally divided, different values of a are respectively selected, and calculation is carried out
And Wj,kThe difference value of the two is obtained by calculating 59 times for balancing the operation speed and the denoising effect, and when n is 8, the operation speed is not influenced, and the denoising effect can be enhanced.
(3) Obtaining
And Wj,kWhen the difference between the two is minimal
And performing wavelet inverse transformation to obtain a de-noised signal.
S3: and (4) conducting wire edge positioning is carried out on the preprocessed power distribution network overhead line image by applying machine vision and a machine learning algorithm. It should be further noted that the positioning of the edge of the wire includes:
roughly determining the edge position of the lead by using the straight line segment of the edge of the lead obtained by the straight line segment detection;
dividing straight line segments of the edge of the conducting wire by using an improved K-means clustering algorithm;
and obtaining a smooth wire edge by a fitting mode.
The straight line segment detection comprises the following steps:
compressing the length and the width of the preprocessed image to 80% of the original size so as to weaken the sawtooth effect when the pixel points form straight-line segments;
respectively carrying out convolution operation on the reduced image and a convolution kernel to obtain gradients G in the x direction and the y directionx、GyAnd the edge points of the image are searched after the gradient magnitude is calculated, as follows,
wherein G is the edge point of the image which is searched after the gradient amplitude value starts, Gx、GyThe gradient in the x direction and the gradient in the y direction respectively.
And (3) classifying and fitting the straight line segments:
the method comprises the steps that the edge positions of conducting wires can be roughly determined through straight-line segment detection of obtained conducting wire edge straight-line segments, considering that a plurality of conducting wires possibly exist in an image at the same time, the side edge of the conducting wire from which each straight-line segment comes is uncertain, further classification is needed to determine the attribution of the conducting wire, and the source of the conducting wire can be determined through a clustering method;
taking a reference line in the image, and calculating the distance from each straight line segment to the reference line;
judging the edge according to the distance;
if the slopes of the straight line segments are different and the straight line segments are not parallel to the reference line, the distance between the straight line segments and the reference line cannot be calculated, and the straight line segments are processed.
The treatment comprises the following steps:
defining the slope and intercept of n straight line segments as k1,k2,…,knAnd b1,b2,…,bnDividing the lead wires into m types, wherein m is 2 times of the number of the lead wires;
arbitrarily taking a reference point and coordinates in the imageIs (x)0,y0)，0＜x0＜h，0＜y0< w, where h, w are the image height and width, respectively;
over reference point (x)0,y0) Are respectively represented by k1,k2,…,knTaking the slope as a reference line, and calculating the distance d from each reference line to the corresponding straight line segmenti(i-1, 2, …, n), as follows,
with (d)i,ki) Denotes the ith straight line segment, will (d)i,ki) All the i-1, 2, …, n are substituted into the K-means clustering algorithm to be classified into m types, and the classification of all the straight line segments in the image is completed;
and taking the head and tail end points of each straight line segment as characteristic points, and fitting each point by using a least square method to obtain a smooth edge of the wire.
S4: and calculating the ice coating thickness of the overhead line and outputting a monitoring result. It should be further noted that the step of calculating the ice thickness of the overhead line includes:
judging the icing state of the overhead line according to the positioned conductor;
the width values of the wires before and after icing are respectively calculated due to the difference of the widths of the wires before and after icing, and the difference value of the width values of the wires before and after icing is taken as a criterion;
calculating the real-time width W of the wire1Then subtracting the diameter W of the ice-free wire2I.e. the current ice layer thickness.
The monitoring result comprises the following steps: icing conditions, ice layer thickness, errors and time consuming.
Example 2
In order to better verify and explain the technical effects adopted in the method of the present invention, the embodiment selects a method applied in an experiment to perform a performance test, and compares the experimental results by a scientific demonstration means to verify the real effects of the method of the present invention.
Conditions for application of the present exampleBased on the description of example 1, a point (x) on a side edge of a conductive line is taken0,y0) The distance from this point to the other side edge of the wire is calculated as follows:
wherein a, b and c are coefficients of a wire edge equation.
The calculated width value is the pixel width of the wire, and the value is not visual enough for operation and maintenance personnel and cannot directly judge the ice coating condition of the line at the moment, so that the calculated width value needs to be further converted into the real width according to the following formula:
the method comprises the steps of obtaining a current real width of a wire, obtaining a current pixel width of the wire by an algorithm in real time, obtaining the current real width of the wire by the algorithm, obtaining the actual diameter of an ice-free line according to the type of the wire, obtaining the pixel width of the ice-free wire by the algorithm, shooting a clear and complete wire image under a clear weather condition, and obtaining a reference value of the pixel width of the ice-free wire by the algorithm.
And after calculating the real-time width D of the line, subtracting the diameter W of the line without ice coating to obtain the thickness of the ice layer at the moment, performing comprehensive analysis on the thickness of the ice layer in combination with historical ice coating data, and judging the ice coating degree of the line at the moment, thereby realizing the monitoring of the ice coating state and the measurement and calculation of the thickness of the overhead line of the distribution network.
The results obtained using the above method in an experimental environment were as follows:
a first wire: the thickness of the ice coating is 0.04cm, and the ice coating state is the non-ice coating state;
a second wire: the thickness of the ice coating is 1.61cm, and the ice coating state is ice coating;
and outputting the monitoring result of the icing state of the overhead line of the distribution network, wherein the output result is shown in the table 1.
Table 1: and monitoring results in an experimental environment.
Referring to table 1, the method for monitoring the icing thickness of the overhead line of the power distribution network based on the improved K-means clustering can accurately identify the lines in different states, errors are less than 0.1cm, and when the accuracy of the line width monitoring result is high, the accuracy of the calculation result of the icing thickness is also high; considering that the line icing is a continuous process, the time required by the icing formation and the ablation is calculated in minutes or even hours, the time required by the method for processing the image is less than 1.5s, the real-time requirement is obviously met, and the precision, the speed and the identification result of the method meet the actual requirement and have higher practical value.
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (3)
1. A power distribution network overhead line icing thickness monitoring method for improving K-means clustering is characterized by comprising the following steps: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
acquiring an image of the overhead line of the power distribution network by using a monocular camera;
preprocessing the power distribution network overhead line image according to a machine vision strategy;
conducting wire edge positioning on the preprocessed power distribution network overhead line image by applying a machine vision and machine learning algorithm;
calculating the ice coating thickness of the overhead line and outputting a monitoring result;
wherein, the step of wire edge positioning includes:
determining the edge position of the lead through the straight line segment of the edge of the lead obtained by the straight line segment detection;
dividing the straight line segments of the edge of the conducting wire by using an improved K-means clustering algorithm;
obtaining a smooth wire edge in a fitting mode;
the step of detecting the straight line segment comprises the following steps:
compressing the length and the width of the preprocessed image to 80% of the original size so as to weaken the sawtooth effect when the pixel points form straight-line segments;
respectively carrying out convolution operation on the reduced image and a convolution kernel to obtain gradients G in the x direction and the y directionx、GyAnd the edge points of the image are searched after the gradient magnitude is calculated, as follows,
wherein G is the edge point of the image which is searched after the gradient amplitude value starts, Gx、GyThe gradients in the x and y directions respectively;
the specific steps of dividing the straight line segments of the wire edge by using the improved K-means clustering algorithm comprise:
taking a reference line in the image, and calculating the distance from each straight line segment to the reference line;
judging the edge according to the distance;
if the slopes of the straight line segments are different and the straight line segments are not parallel to the datum line, the distance between the straight line segments and the datum line cannot be calculated, and then the straight line segments are processed;
the processing comprises the following steps:
defining the slope and intercept of n straight line segments as k1,k2,…,knAnd b1,b2,…,bnDividing the lead wires into m types, wherein m is 2 times of the number of the lead wires;
arbitrarily taking a reference point in the image, the coordinate is (x)0,y0)，0＜x0＜h，0＜y0< w, where h, w are the image height and width, respectively;
also comprises the following steps of (1) preparing,
over reference point (x)0,y0) Are respectively represented by k1,k2,…,knTaking the slope as a reference line, and calculating the distance d from each reference line to the corresponding straight line segmentiWherein i is 1,2, …, n; as follows below, the following description will be given,
with (d)i,ki) Denotes the ith straight line segment, will (d)i,ki) All the straight line segments are substituted into a K mean value clustering algorithm to be divided into m types, and then all the straight line segments in the image are divided;
further, the step of calculating the ice thickness of the overhead line comprises:
judging the icing state of the overhead line according to the positioned conductor;
the width values of the wires before and after icing are respectively calculated due to the difference of the widths of the wires before and after icing, and the difference value of the width values of the wires before and after icing is taken as a criterion;
calculating the real-time width W of the wire1Then subtracting the diameter W of the ice-free wire2I.e. the current ice layer thickness.
2. The method for monitoring the icing thickness of the overhead lines of the power distribution network based on the improved K-means clustering is characterized by comprising the following steps of: the preprocessing comprises image filtering, morphological operation, ashing degree, contrast enhancement and image denoising.
3. The method for monitoring the icing thickness of the overhead lines of the power distribution network based on the improved K-means clustering is characterized by comprising the following steps of: the monitoring results comprise the icing state, the ice layer thickness, errors and time-consuming duration.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110796620.0A CN113538371B (en) | 2021-07-14 | 2021-07-14 | Power distribution network overhead line icing thickness monitoring method for improving K-means clustering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110796620.0A CN113538371B (en) | 2021-07-14 | 2021-07-14 | Power distribution network overhead line icing thickness monitoring method for improving K-means clustering |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113538371A CN113538371A (en) | 2021-10-22 |
| CN113538371B true CN113538371B (en) | 2022-05-17 |
Family
ID=78128031
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110796620.0A Active CN113538371B (en) | 2021-07-14 | 2021-07-14 | Power distribution network overhead line icing thickness monitoring method for improving K-means clustering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113538371B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106595500A (en) * | 2016-11-21 | 2017-04-26 | 云南电网有限责任公司电力科学研究院 | Transmission line ice coating thickness measurement method based on unmanned aerial vehicle binocular vision |
| CN107389014A (en) * | 2017-07-20 | 2017-11-24 | 云南电网有限责任公司电力科学研究院 | A kind of electric power line ice-covering thickness Forecasting Methodology |
| CN110533331A (en) * | 2019-08-30 | 2019-12-03 | 广东电网有限责任公司江门供电局 | A kind of fault early warning method and system based on transmission line of electricity data mining |
| CN110826179A (en) * | 2019-09-29 | 2020-02-21 | 贵州电网有限责任公司 | Intelligent substation relay protection real-time reliability prediction method |
| CN111951520A (en) * | 2020-07-31 | 2020-11-17 | 国网福建省电力有限公司宁德供电公司 | System and method for detecting icing thickness of transmission line conductor |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7883609B2 (en) * | 1998-06-15 | 2011-02-08 | The Trustees Of Dartmouth College | Ice modification removal and prevention |
-
2021
- 2021-07-14 CN CN202110796620.0A patent/CN113538371B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106595500A (en) * | 2016-11-21 | 2017-04-26 | 云南电网有限责任公司电力科学研究院 | Transmission line ice coating thickness measurement method based on unmanned aerial vehicle binocular vision |
| CN107389014A (en) * | 2017-07-20 | 2017-11-24 | 云南电网有限责任公司电力科学研究院 | A kind of electric power line ice-covering thickness Forecasting Methodology |
| CN110533331A (en) * | 2019-08-30 | 2019-12-03 | 广东电网有限责任公司江门供电局 | A kind of fault early warning method and system based on transmission line of electricity data mining |
| CN110826179A (en) * | 2019-09-29 | 2020-02-21 | 贵州电网有限责任公司 | Intelligent substation relay protection real-time reliability prediction method |
| CN111951520A (en) * | 2020-07-31 | 2020-11-17 | 国网福建省电力有限公司宁德供电公司 | System and method for detecting icing thickness of transmission line conductor |
Non-Patent Citations (6)
| Title |
|---|
| 《Research on Data Mining of Wind Disaster of Power Transmission Line Based on Clustering Analysis》;Li Peng等;《2019 6th International Conference on Information Science and Control Engineering (ICISCE)》;20200604;第 459-463页 * |
| 《Voltage Balancing Scheme Based on Active Voltage Cross Control for Series-Connected IGBTs》;Jiahong Liu等;《2020 IEEE 9th International Power Electronics and Motion Control Conference (IPEMC2020-ECCE Asia) 》;20210309;第2588-2593页 * |
| 《一种基于改进K均值聚类的输电线路覆冰状态侦测方法》;翁秉钧等;《电气技术》;20210531;第22卷(第5期);第43-49页 * |
| 《基于全局-局部密度的准完全二分子图建模与挖掘方法》;时磊等;《计算机应用与软件》;20181231;第35卷(第12期);第241-246页 * |
| 《电力企业的节能降耗》;邓俐岚;《农电管理》;20170531(第5期);第39-40页 * |
| 《输电线路实际运行中的防雷技术》;吴瑀等;《通信电源技术》;20200831;第37卷(第8期);第91-93+97页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113538371A (en) | 2021-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109118479B (en) | Capsule network-based insulator defect identification and positioning device and method | |
| CN107507194B (en) | Insulator string fault detection method based on infrared image temperature distribution rule and BP neural network | |
| CN108734689B (en) | Method for detecting scattered strands of conducting wires based on region growth | |
| CN111784633B (en) | Insulator defect automatic detection algorithm for electric power inspection video | |
| CN108108772B (en) | Insulator pollution flashover state detection method based on aerial image of distribution line | |
| CN108986104B (en) | Insulator image segmentation method based on distance transformation and watershed marking algorithm | |
| CN109523543B (en) | Method for detecting broken strands of conducting wires based on edge distance | |
| CN108680833B (en) | Composite insulator defect detection system based on unmanned aerial vehicle | |
| CN109342909B (en) | SLLE-based cable accessory partial discharge mode identification method | |
| CN107179479B (en) | Visible light image-based transmission conductor strand scattering defect detection method | |
| CN111507975B (en) | Method for detecting abnormity of outdoor insulator of traction substation | |
| CN108734704B (en) | Transmission conductor strand breakage detection method based on gray variance normalization | |
| CN113051423A (en) | Intelligent online monitoring method for state of power transmission line of intelligent power grid based on big data analysis | |
| CN109684905A (en) | The method of the icing quality testing of aerial condutor based on image identification | |
| CN113592324A (en) | Cable terminal tower live-line work risk assessment method based on hierarchical analysis | |
| CN115205256A (en) | Power transmission line insulator defect detection method and system based on fusion of transfer learning | |
| Zhang et al. | Detection and condition assessment of icicle bridging for suspension glass insulator by image analysis | |
| CN111667473A (en) | Insulator hydrophobicity grade judging method based on improved Canny algorithm | |
| CN108734709B (en) | Insulator flange shape parameter identification and damage detection method | |
| CN117409083B (en) | Cable terminal identification method and device based on infrared image and improved YOLOV5 | |
| CN113538371B (en) | Power distribution network overhead line icing thickness monitoring method for improving K-means clustering | |
| CN109903258B (en) | Power cable category detection method and system based on gray level matching | |
| CN116538924A (en) | Real-time monitoring method for sag of power transmission line in icing state | |
| CN108492292B (en) | Infrared image processing-based wire strand scattering detection method | |
| CN115439319A (en) | Exposed detection method for electric slide wire protection device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |