CN111695506A - Wind-induced foreign matter short-circuit fault early warning method and system for power transmission line - Google Patents

Abstract

The invention discloses a wind-induced foreign object short-circuit fault early warning method and system for a power transmission line. The method includes the following steps: Step 1: collect historical wind-induced foreign object short-circuit image information, and distinguish and mark according to faults and non-faults; step 2: historical images Perform image processing, extract the short-circuit characteristics of foreign objects in the power grid from the processed historical images, and establish a typical wire foreign object comparison library for the short-circuit characteristics of foreign objects in the power grid; Step 3: According to the importance of the line, geographical features and the distribution map of the power grid wind zone, establish the distribution geography of hidden dangers in the channel Step 4: Obtain the real-time visual channel image information of the transmission line, and identify foreign objects on the real-time visual channel image; Step 5: Early warning of foreign objects on the transmission line, and push the warning information to the responsibility of the transmission line people. The present invention realizes early warning and real-time warning for short circuit of foreign objects caused by wind.

Description

Method and system for early warning of short-circuit fault caused by wind in power transmission lines

technical field

The invention relates to a wind-induced foreign object short-circuit fault early warning method and system for power transmission lines, and belongs to the technical field of overhead power transmission line operation and maintenance.

Background technique

Overhead transmission lines operate in the field all year round, and are greatly affected by external natural conditions. Under extreme weather conditions such as thunderstorms, typhoons, and freezing rain, it is easy to cause tripping faults, affecting the reliability of power supply, and even in special circumstances may lead to large areas of the power grid. Long-term power outages occur, and transmission line failures caused by wind disasters have brought huge losses to the power system and brought great inconvenience to production and life.

Wind-induced foreign body short-circuiting has become an important factor restricting the safe and stable operation of power grid lines. Foreign objects that cause foreign objects to short-circuit and trip on transmission lines include plastic greenhouses, mulch, reflective films, balloons, sunscreens, advertising cloths, aluminum foils, and other objects with large surface areas, which are easily blown on the transmission lines by the wind.

At present, many mature patents have proposed detection methods for foreign objects on transmission lines, or drone-based aerial photography foreign object image recognition methods, wire foreign object cleaning devices, etc. However, the above-mentioned patents are basically based on a simple image recognition method to realize the recognition of foreign objects. At present, this kind of simple visual monitoring device can accurately identify the two main external break factors of cranes and construction machinery, but the accuracy of the identification of wire foreign objects is low, and the overall work needs to be further improved.

Therefore, it is very important to establish a complete set of wind-induced foreign object short-circuit fault judgment and analysis methods.

SUMMARY OF THE INVENTION

In order to solve the above problems, the present invention proposes a wind-induced foreign object short-circuit fault early warning method and system for transmission lines, which can realize early warning and real-time alarm for wind-induced foreign object short-circuit, can prevent potential channel hidden faults in advance and provide a basis for fault analysis. Information support to escort the safe and stable operation of power grid transmission lines.

The technical scheme adopted by the present invention to solve its technical problems is:

On the one hand, a wind-induced foreign object short-circuit fault warning method for a power transmission line provided by an embodiment of the present invention includes the following steps:

Step 1: Collect historical short-circuit image information of foreign objects caused by wind-induced faults, and mark the historical visualization channel images according to faults and non-faults;

Step 2: Perform grayscale processing, histogram calculation, image enhancement and noise filtering processing on the historical images in turn. The Hough algorithm and the inchworm creep fusion method are used to extract the short-circuit characteristics of power grid foreign objects from the processed historical images. Short-circuit characteristics establish a typical wire foreign body comparison library;

Step 3: According to the importance of the line, the geographical characteristics and the distribution map of the power grid wind area, a geographical map of the distribution of hidden dangers in the channel is established, and the types of hidden danger areas are divided;

Step 4: Obtain the real-time visual channel image information of the transmission line, and use the methods described in steps 1 to 3 to identify foreign objects on the real-time visual channel image;

Step 5: Early warning of foreign objects in the transmission line, and push the warning information to the responsible person of the transmission line.

As a possible implementation manner of this embodiment, the typical wire foreign object comparison library includes a plastic film comparison library, a reflective film comparison library, a kite comparison library, a balloon comparison library, and other foreign object comparison libraries.

As a possible implementation of this embodiment, the historical visualization channel image and the real-time visualization channel image both include a typical channel image in spring, a typical channel image in summer, a typical channel image in autumn, and a typical channel image in winter, and the typical channel image in spring The background color of the typical channel image is dry yellow or tender green, the background color of the typical channel image in summer is green with uniform color, the background color of the typical channel image in autumn is mixed color, and the background color of the typical channel image in winter is yellow or white .

As a possible implementation manner of this embodiment, the step 2 is specifically:

The Canny method is used to extract the edge, and the Hough transform is realized according to the Hough transform formula of the straight line. After finding the maximum Hough value and setting the threshold, it is inversely transformed to the image RGB value space, and the image value after the Hough transform is obtained;

The inchworm creeping algorithm is used to set the origin coordinates in the image and determine the initial search point of the wire, and then select along the direction of the wire search to determine the characteristics of the wire, and obtain an accurate wire identification image.

As a possible implementation manner of this embodiment, the degree of importance of the lines includes UHV/cross-regional lines, mountain lines, power-protected lines, three-span lines, 220kV and above important multi-circuit lines on the same tower and general lines; the The geographical features include greenhouse areas, garbage dumps, temporary construction areas and other areas; the distribution map of the power grid wind area is the distribution map of three types of power grid wind areas that occur once in 30 years, 50 years and 100 years.

As a possible implementation manner of this embodiment, the step 4 is specifically:

Collect real-time visual channel image information of transmission lines;

Use the non-faulty image and the real-time visualization channel image to overlap and compare, and filter out the faulty image;

Use the typical wire foreign body comparison gallery and the geographical features of the area where the line belongs to determine the type of suspected foreign body on the wire.

As a possible implementation manner of this embodiment, the method further includes the following steps:

Step 6: Collect the on-site meteorological data of the transmission line, and determine the wind speed in the area where the transmission line is located in combination with the meteorological data of the meteorological department in the area of the transmission line, and set the wind-induced foreign object short-circuit risk warning level according to the meteorological wind speed and surrounding geographical characteristics.

As a possible implementation manner of this embodiment, the step 6 is specifically:

Collect the micro-meteorological data near the poles and towers of the transmission line and the meteorological data of the local meteorological department;

The wind speed in the area where the line is located is judged, and the wind speed is divided into three grades: clear wind, strong wind and strong wind;

Combine the wind speed and the characteristics of the area where the line belongs to early warning to judge the level of short circuit caused by the wind.

On the other hand, a wind-induced foreign object short-circuit fault warning system for a power transmission line provided by an embodiment of the present invention includes:

The fault discrimination module is used to collect historical short-circuit image information of foreign objects caused by wind-induced faults, and to distinguish and mark the historical visualization channel images according to faults and non-faults;

The feature extraction module is used to sequentially perform grayscale processing, histogram calculation, image enhancement and noise filtering processing on the historical images. The Hough algorithm and the inchworm creep fusion method are used to extract the short-circuit features of foreign objects in the power grid from the processed historical images. According to the short-circuit characteristics of foreign objects in the power grid, a typical wire foreign object comparison library is established;

The type division module is used to establish a geographical map of the distribution of hidden dangers in the passage according to the importance of the line, the geographical characteristics and the distribution map of the power grid wind area, and to divide the types of hidden danger areas;

The foreign object identification module is used to obtain the real-time visual channel image information of the transmission line, and perform foreign object identification on the real-time visual channel image;

The early warning module is used for early warning of foreign objects in the transmission line, and pushes the warning information to the responsible person of the transmission line.

As a possible implementation manner of this embodiment, the typical wire foreign object comparison library includes a plastic film comparison library, a reflective film comparison library, a kite comparison library, a balloon comparison library, and other foreign object comparison libraries.

As a possible implementation of this embodiment, the historical visualization channel image and the real-time visualization channel image both include a typical channel image in spring, a typical channel image in summer, a typical channel image in autumn, and a typical channel image in winter, and the typical channel image in spring The background color of the typical channel image is dry yellow or tender green, the background color of the typical channel image in summer is green with uniform color, the background color of the typical channel image in autumn is mixed color, and the background color of the typical channel image in winter is yellow or white .

As a possible implementation manner of this embodiment, the feature extraction module is specifically used for:

The Canny method is used to extract the edge, and the Hough transform is realized according to the Hough transform formula of the straight line. After finding the maximum Hough value and setting the threshold, it is inversely transformed to the image RGB value space, and the image value after the Hough transform is obtained;

The inchworm creeping algorithm is used to set the origin coordinates in the image and determine the initial search point of the wire, and then select along the direction of the wire search to determine the characteristics of the wire, and obtain an accurate wire identification image.

As a possible implementation manner of this embodiment, the degree of importance of the lines includes UHV/cross-regional lines, mountain lines, power-protected lines, three-span lines, 220kV and above important multi-circuit lines on the same tower and general lines; the The geographical features include greenhouse areas, garbage dumps, temporary construction areas and other areas; the distribution map of the power grid wind area is the distribution map of three types of power grid wind areas that occur once in 30 years, 50 years and 100 years.

As a possible implementation manner of this embodiment, the foreign object identification module is specifically used for:

Collect real-time visual channel image information of transmission lines;

Use the non-faulty image and the real-time visualization channel image to overlap and compare, and filter out the faulty image;

Use the typical wire foreign body comparison gallery and the geographical features of the area where the line belongs to determine the type of suspected foreign body on the wire.

As a possible implementation manner of this embodiment, the system further includes:

The risk warning module is used to collect the on-site meteorological data of the transmission line, and combine the meteorological data of the meteorological department in the area described by the transmission line to determine the wind speed of the area where the transmission line is located, and set the wind-induced foreign object short-circuit risk warning level according to the meteorological wind speed and surrounding geographical characteristics. .

As a possible implementation manner of this embodiment, the risk early warning module is specifically used for:

Collect the micro-meteorological data near the poles and towers of the transmission line and the meteorological data of the local meteorological department;

The wind speed in the area where the line is located is judged, and the wind speed is divided into three grades: clear wind, strong wind and strong wind;

Combine the wind speed and the characteristics of the area where the line belongs to early warning to judge the level of short circuit caused by the wind.

The beneficial effects that the technical solutions of the embodiments of the present invention can have are as follows:

In order to overcome the shortcomings of only relying on traditional images or UAV aerial photography images for wire foreign body identification, and the shortcomings of inability to combine channel hidden danger information for comprehensive early warning and analysis and judgment, the present invention combines historical wind-induced fault scene pictures, four seasons typical channel visualization images, Based on the information such as fault pictures of wire foreign body short-circuit, line wire detection is carried out based on the combination of Hough transform and inchworm creeping method, and a typical wire foreign body short circuit library is established; based on the existing visual monitoring device, line micro-meteorological monitoring device and meteorological data of meteorological departments , according to the importance of the line, the geographical features and the distribution map of the power grid wind area, the classification method of the hidden danger area and the distribution geographical map of the hidden danger of the channel are established; through the combination of the real-time visual image in the channel and the information of the hidden danger in the area, the real-time analysis and judgment of whether the conductor has suspected foreign objects and the type of foreign objects, And real-time alarm; combined with the meteorological information, the comprehensive wind speed and the distribution map of hidden dangers in the channel to achieve the three-level risk early warning of wind-induced foreign object short circuit. The invention comprehensively considers the influence of multiple factors on the wind-induced foreign body short circuit, realizes the early warning and real-time alarm for the wind-induced foreign body short circuit, can prevent potential channel hidden faults in advance, provide basic information support for fault analysis, and provide power transmission for the power grid. The safe and stable operation of the line is escorted.

Compared with the prior art, the present invention has the following characteristics:

1) The present invention fully combines the existing work results and systems of grid visualization image monitoring, relying on the channel visualization image information collected in the past three years and the fault information in the past 10 years as sample training, and establishes a typical background based on the four seasons of spring, summer, autumn and winter. Channel comparison gallery and five types of wire foreign body comparison gallery under conditions;

2) Introduce a high-precision wire detection algorithm fused with Hough and inchworm creeping algorithms, and improve the accuracy of wire identification by complementing and integrating the two algorithms;

3) Establish a geographical map of the distribution of hidden dangers in the passage according to the importance of the line, and propose a wind-induced foreign object short-circuit risk early warning and real-time warning method that integrates meteorology, visual images, wind zone maps and geographic feature information. and real-time alarms, the judgment and analysis methods are more accurate;

4) The method of the invention is simple to use, has strong feasibility and high prediction accuracy, and can provide a reference for the judgment of short-circuit faults caused by wind-induced foreign objects in line operation and maintenance departments.

Description of drawings:

FIG. 1 is a flowchart of a method for early warning of a short-circuit fault caused by wind-induced foreign objects in a power transmission line according to an exemplary embodiment;

FIG. 2 is a structural diagram of a wind-induced foreign object short-circuit fault early warning system for a power transmission line according to an exemplary embodiment;

Fig. 3 is the basic image processing flow chart of the present invention;

FIG. 4 is a flow chart of the implementation of the present invention for the early warning analysis of the line wind-induced short-circuit fault.

Detailed ways

Below in conjunction with accompanying drawing and embodiment, the present invention will be further described:

In order to clearly illustrate the technical features of the solution, the present invention will be described in detail below through specific embodiments and in conjunction with the accompanying drawings. The following disclosure provides many different embodiments or examples for implementing different structures of the invention. In order to simplify the disclosure of the present invention, the components and arrangements of specific examples are described below. Furthermore, the present invention may repeat reference numerals and/or letters in different instances. This repetition is for the purpose of simplicity and clarity and does not in itself indicate a relationship between the various embodiments and/or arrangements discussed. It should be noted that the components illustrated in the figures are not necessarily drawn to scale. Descriptions of well-known components and processing techniques and processes are omitted from the present invention to avoid unnecessarily limiting the present invention.

FIG. 1 is a flow chart of a method for early warning of a short-circuit fault caused by wind-induced foreign objects in a power transmission line according to an exemplary embodiment. As shown in FIG. 1 , a method for early warning of short-circuit fault caused by wind in a power transmission line provided by an embodiment of the present invention includes the following steps:

Step 1: Collect historical short-circuit image information of foreign objects caused by wind-induced faults, and mark the historical visualization channel images according to faults and non-faults;

Step 2: Perform grayscale processing, histogram calculation, image enhancement and noise filtering processing on the historical images in turn. The Hough algorithm and the inchworm creep fusion method are used to extract the short-circuit characteristics of power grid foreign objects from the processed historical images. Short-circuit characteristics establish a typical wire foreign body comparison library;

Step 3: According to the importance of the line, the geographical characteristics and the distribution map of the power grid wind area, a geographical map of the distribution of hidden dangers in the channel is established, and the types of hidden danger areas are divided;

Step 4: Obtain the real-time visual channel image information of the transmission line, and use the methods described in steps 1 to 3 to identify foreign objects on the real-time visual channel image;

Step 5: Early warning of foreign objects in the transmission line, and push the warning information to the responsible person of the transmission line.

As a possible implementation manner of this embodiment, the typical wire foreign object comparison library includes a plastic film comparison library, a reflective film comparison library, a kite comparison library, a balloon comparison library, and other foreign object comparison libraries.

As a possible implementation of this embodiment, the historical visualization channel image and the real-time visualization channel image both include a typical channel image in spring, a typical channel image in summer, a typical channel image in autumn, and a typical channel image in winter, and the typical channel image in spring The background color of the typical channel image is dry yellow or tender green, the background color of the typical channel image in summer is green with uniform color, the background color of the typical channel image in autumn is mixed color, and the background color of the typical channel image in winter is yellow or white .

As a possible implementation manner of this embodiment, the step 2 is specifically:

The Canny method is used to extract the edge, and the Hough transform is realized according to the Hough transform formula of the straight line. After finding the maximum Hough value and setting the threshold, it is inversely transformed to the image RGB value space, and the image value after the Hough transform is obtained;

The inchworm creeping algorithm is used to set the origin coordinates in the image and determine the initial search point of the wire, and then select along the direction of the wire search to determine the characteristics of the wire, and obtain an accurate wire identification image.

As a possible implementation manner of this embodiment, the degree of importance of the lines includes UHV/cross-regional lines, mountain lines, power-protected lines, three-span lines, 220kV and above important multi-circuit lines on the same tower and general lines; the The geographical features include greenhouse areas, garbage dumps, temporary construction areas and other areas; the distribution map of the power grid wind area is the distribution map of three types of power grid wind areas that occur once in 30 years, 50 years and 100 years.

As a possible implementation manner of this embodiment, the step 4 is specifically:

Collect real-time visual channel image information of transmission lines;

Use the non-faulty image and the real-time visualization channel image to overlap and compare, and filter out the faulty image;

Use the typical wire foreign body comparison gallery and the geographical features of the area where the line belongs to determine the type of suspected foreign body on the wire.

As a possible implementation manner of this embodiment, the method further includes the following steps:

Step 6: Collect the on-site meteorological data of the transmission line, and determine the wind speed in the area where the transmission line is located in combination with the meteorological data of the meteorological department in the area of the transmission line, and set the wind-induced foreign object short-circuit risk warning level according to the meteorological wind speed and surrounding geographical characteristics.

As a possible implementation manner of this embodiment, the step 6 is specifically:

Collect the micro-meteorological data near the poles and towers of the transmission line and the meteorological data of the local meteorological department;

The wind speed in the area where the line is located is judged, and the wind speed is divided into three grades: clear wind, strong wind and strong wind;

Combine the wind speed and the characteristics of the area where the line belongs to early warning to judge the level of short circuit caused by the wind.

FIG. 2 is a structural diagram of a wind-induced foreign object short-circuit fault early warning system for a power transmission line according to an exemplary embodiment. As shown in FIG. 2 , a wind-induced foreign object short-circuit fault warning system for a power transmission line provided by an embodiment of the present invention includes:

The fault discrimination module is used to collect historical short-circuit image information of foreign objects caused by wind-induced faults, and to distinguish and mark the historical visualization channel images according to faults and non-faults;

The feature extraction module is used to sequentially perform grayscale processing, histogram calculation, image enhancement and noise filtering processing on the historical images. The Hough algorithm and the inchworm creep fusion method are used to extract the short-circuit features of foreign objects in the power grid from the processed historical images. According to the short-circuit characteristics of foreign objects in the power grid, a typical wire foreign object comparison library is established;

The type division module is used to establish a geographical map of the distribution of hidden dangers in the passage according to the importance of the line, the geographical characteristics and the distribution map of the power grid wind area, and to divide the types of hidden danger areas;

The foreign object identification module is used to obtain the real-time visual channel image information of the transmission line, and perform foreign object identification on the real-time visual channel image;

The early warning module is used for early warning of foreign objects in the transmission line, and pushes the warning information to the responsible person of the transmission line.

As a possible implementation manner of this embodiment, the typical wire foreign object comparison library includes a plastic film comparison library, a reflective film comparison library, a kite comparison library, a balloon comparison library, and other foreign object comparison libraries.

As a possible implementation of this embodiment, the historical visualization channel image and the real-time visualization channel image both include a typical channel image in spring, a typical channel image in summer, a typical channel image in autumn, and a typical channel image in winter, and the typical channel image in spring The background color of the typical channel image is dry yellow or tender green, the background color of the typical channel image in summer is green with uniform color, the background color of the typical channel image in autumn is mixed color, and the background color of the typical channel image in winter is yellow or white .

As a possible implementation manner of this embodiment, the feature extraction module is specifically used for:

The Canny method is used to extract the edge, and the Hough transform is realized according to the Hough transform formula of the straight line. After finding the maximum Hough value and setting the threshold, it is inversely transformed to the image RGB value space, and the image value after the Hough transform is obtained;

The inchworm creeping algorithm is used to set the origin coordinates in the image and determine the initial search point of the wire, and then select along the direction of the wire search to determine the characteristics of the wire, and obtain an accurate wire identification image.

As a possible implementation manner of this embodiment, the degree of importance of the lines includes UHV/cross-regional lines, mountain lines, power-protected lines, three-span lines, 220kV and above important multi-circuit lines on the same tower and general lines; the The geographical features include greenhouse areas, garbage dumps, temporary construction areas and other areas; the distribution map of the power grid wind area is the distribution map of three types of power grid wind areas that occur once in 30 years, 50 years and 100 years.

As a possible implementation manner of this embodiment, the foreign object identification module is specifically used for:

Collect real-time visual channel image information of transmission lines;

Use the non-faulty image and the real-time visualization channel image to overlap and compare, and filter out the faulty image;

Use the typical wire foreign body comparison gallery and the geographical features of the area where the line belongs to determine the type of suspected foreign body on the wire.

As a possible implementation manner of this embodiment, the system further includes:

The risk warning module is used to collect the on-site meteorological data of the transmission line, and combine the meteorological data of the meteorological department in the area described by the transmission line to determine the wind speed of the area where the transmission line is located, and set the wind-induced foreign object short-circuit risk warning level according to the meteorological wind speed and surrounding geographical characteristics. .

As a possible implementation manner of this embodiment, the risk early warning module is specifically used for:

Collect the micro-meteorological data near the poles and towers of the transmission line and the meteorological data of the local meteorological department;

The wind speed in the area where the line is located is judged, and the wind speed is divided into three grades: clear wind, strong wind and strong wind;

Combine the wind speed and the characteristics of the area where the line belongs to early warning to judge the level of short circuit caused by the wind.

In order to better understand the present invention, how to establish a reliable image recognition method for foreign objects in wires, use a visual monitoring device and meteorological data to realize early warning and early warning of foreign object short-circuits under strong wind conditions in combination with the actual operation of Shandong Power Grid and existing data. Real-time alarm, establish a complete set of wind-induced foreign object short-circuit fault judgment and analysis measures.

As shown in Figures 3 and 4, the present invention fully combines the existing work results and systems of Shandong power grid visualization image monitoring, relying on the channel visualization image information collected in the past three years and the fault information in the past 10 years as sample training, and establishes a model based on spring, Channel comparison gallery and five types of wire foreign body comparison gallery under typical background conditions in summer, autumn and winter, introduce high-precision wire detection algorithm combined with Hough and inchworm creeping algorithms, through the complement and fusion of the two algorithms, improve the identification of wire accuracy, including the following steps:

Step 1: Collect photos of 110kV and above wind-induced foreign object short-circuit faults in Shandong Power Grid over the past 10 years and the image information before and after the wind-induced foreign object short-circuit fault collected after the installation of the first visual monitoring device in 2016, and organize the image information according to spring and summer. According to the characteristics of Shandong power grid, feature extraction is carried out according to the background color and background scene, among which the background color in spring is dry yellow or bright green, the background in summer is green with uniform color, and the background color in autumn is complex (yellow). , red, green and other colors are available), the winter background color is yellow or white;

Step 2: Image processing and feature extraction, performing grayscale processing, histogram calculation, image enhancement, and noise filtering on the image to enhance the effective features of the image;

When identifying the wire in the visual image, the wire can be divided into a series of discrete points in the image. First, the non-faulty image collected by the visual monitoring device is preprocessed, and the Canny method is used for edge extraction to extract the image with edge information. According to the Hough change of the straight line, the conversion from point to curve is realized, each pixel coordinate point (X, Y) is converted to the (ρ, θ) curve point, the maximum Hough value is found, the threshold P is set, the wire is identified, and finally Inverse transform the recognized image to the image RGB value and label it, where:

ρ=xcosθ+ysinθ.

On the basis of its wide application, the Hough transform algorithm is limited by its low efficiency and high space occupancy rate, which affects the accuracy of the algorithm. In order to improve the efficiency and speed of wire identification, the inchworm creep method is introduced. According to the approximate position of the wire and the identification result determined by the Hough method, first set the origin coordinates in the image and determine the initial search point of the wire, and then select along the direction of the wire search to determine the characteristics of the wire, and obtain an accurate wire identification image;

Step 3: Identify foreign objects in wires. Based on the identification of wires, combined with the short-circuit characteristics of foreign objects in Shandong Power Grid, the foreign objects are classified into plastic films, reflective films, kites, balloons and other types according to the occurrence frequency of foreign objects in the wires in the past 10 years. Wire Foreign Object Comparison Gallery.

According to the actual operating lines of Shandong Power Grid, a geographical map of hidden danger distribution of passages is established according to the importance of lines, geographical features, and distribution of wind areas. The importance of lines is divided as shown in Table 1. The wind map is divided into 30-year, 50-year and 100-year wind map distribution levels. The hidden dangers of the passage include special attention hidden danger areas, important hidden danger areas and general hidden danger areas.

Table 1: Route importance division

In actual use, it includes two methods: real-time alarm of wind-induced foreign object short circuit and risk warning.

The real-time alarm is the channel visualization image of the visual monitoring device in the connected channel. The basic image processing in Figure 3 is used to analyze and confirm whether there is a wire foreign body. If there is no wire, there will be no real-time alarm; When the line is located, the type of hidden danger area in the area where the line is located and the type of foreign objects that may appear, compare the typical foreign object library, confirm the suspected foreign object in the wire, and push the real-time alarm information of the judgment result to the person in charge of the line through the dual mechanism of SMS and WeChat;

Risk warning is to divide the wind speed into clear wind (3-8m/s), strong wind ( 8～13.8m/s) and strong wind (above 13.8m/s) three grades, in which short-circuit faults caused by kites, balloons, etc. often occur in clear wind conditions, and short-circuit faults caused by plastic films, billboards, etc. often occur in strong wind conditions , short-circuit faults caused by temporary construction facilities often occur in strong wind weather; combined with the wind speed and the type of hidden danger area, the risk warning level of wind-induced foreign objects is set, and the dual message push mechanism of SMS and WeChat is adopted to the responsible person of the line, and the risk level is divided as shown in the table. 2 shown;

Table 2: Classification of risk levels

Based on the background feature images of different seasons images collected by the visual monitoring device, a wire detection method based on the combination of Hough and inchworm creeping method is proposed to realize the dynamic processing and analysis of the images of the visual monitoring device, and establish a typical The comparison gallery of wire foreign objects; combined with the 30-year, 50-year and 100-year wind area distribution map of Shandong Power Grid and the importance of the line to build a channel hidden danger distribution geographic map; comprehensive visual image information, channel hidden danger distribution map and meteorological information, etc. Influenced by multiple factors, it can realize early warning and real-time alarm for wind-induced foreign object short circuit, and can contain potential channel hidden faults in advance and provide basic information support for fault analysis, escorting the safe and stable operation of Shandong power grid transmission lines.

As will be appreciated by those skilled in the art, the embodiments of the present application may be provided as a method, a system, or a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in a flow or flow of a flowchart and/or a block or blocks of a block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions The apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: the present invention can still be Modifications or equivalent replacements are made to the specific embodiments of the present invention, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention shall be included within the protection scope of the claims of the present invention.

Claims (10)

1. a wind-induced foreign object short-circuit fault early warning method for power transmission lines, is characterized in that, comprises the following steps: Step 1: Collect historical short-circuit image information of foreign objects caused by wind-induced faults, and mark the historical visualization channel images according to faults and non-faults; Step 2: Perform grayscale processing, histogram calculation, image enhancement and noise filtering processing on the historical images in turn. The Hough algorithm and the inchworm creep fusion method are used to extract the short-circuit characteristics of power grid foreign objects from the processed historical images. Short-circuit characteristics establish a typical wire foreign body comparison library; Step 3: According to the importance of the line, the geographical characteristics and the distribution map of the power grid wind area, a geographical map of the distribution of hidden dangers in the channel is established, and the types of hidden danger areas are divided; Step 4: Obtain the real-time visual channel image information of the transmission line, and use the methods described in steps 1 to 3 to identify foreign objects on the real-time visual channel image; Step 5: Early warning of foreign objects in the transmission line, and push the warning information to the responsible person of the transmission line. 2. a kind of transmission line wind-induced short-circuit fault early warning method for foreign objects according to claim 1, is characterized in that, described typical wire foreign object comparison gallery comprises plastic film comparison gallery, reflective film comparison gallery, kite comparison gallery, balloon comparison gallery and Other foreign objects comparison gallery. 3. The method for early warning of short-circuit faults caused by wind in power transmission lines according to claim 2, wherein the historical visualization channel image and the real-time visualization channel image include a typical channel image in spring, a typical channel image in summer, and a typical channel image in autumn. image and a typical channel image in winter, the background color of the typical channel image in spring is dry yellow or bright green, the background color of the typical channel image in summer is green with uniform color, and the background color of the typical channel image in autumn is a mixed color, The background color of the winter typical channel image is yellow or white. 4. The method for early warning of short-circuit fault caused by wind in power transmission lines according to claim 1, wherein the step 2 is specifically: The Canny method is used to extract the edge, and the Hough transform is realized according to the Hough transform formula of the straight line. After finding the maximum Hough value and setting the threshold, it is inversely transformed to the image RGB value space, and the image value after the Hough transform is obtained; The inchworm creeping algorithm is used to set the origin coordinates in the image and determine the initial search point of the wire, and then select along the direction of the wire search to determine the characteristics of the wire, and obtain an accurate wire identification image. 5. The method for early warning of short-circuit faults caused by wind in power transmission lines according to claim 1, wherein the importance of the lines includes UHV/cross-regional lines, mountain lines, power-protection lines, three-span lines, 220kV and The above important multi-circuit lines and general lines on the same tower; the geographical features include greenhouse areas, garbage dumps, temporary construction areas and other areas; the distribution map of the power grid wind area is three types of once-in-30-year, 50-year and 100-year Distribution map of type grid wind area. 6. The method for early warning of short-circuit fault caused by wind in a power transmission line according to claim 1, wherein the step 4 is specifically: Collect real-time visual channel image information of transmission lines; Use the non-faulty image and the real-time visualization channel image to overlap and compare, and filter out the faulty image; Use the typical wire foreign body comparison gallery and the geographical features of the area where the line belongs to determine the type of suspected foreign body on the wire. 7. A kind of early warning method for wind-induced foreign body short-circuit fault in power transmission lines according to any one of claims 1-6, characterized in that, further comprising the following steps: Step 6: Collect the on-site meteorological data of the transmission line, and determine the wind speed in the area where the transmission line is located in combination with the meteorological data of the meteorological department in the area of the transmission line, and set the wind-induced foreign object short-circuit risk warning level according to the meteorological wind speed and surrounding geographical characteristics. 8. A method for early warning of short-circuit fault caused by wind in a power transmission line according to claim 7, wherein the step 6 is specifically: Collect the micro-meteorological data near the poles and towers of the transmission line and the meteorological data of the local meteorological department; The wind speed in the area where the line is located is judged, and the wind speed is divided into three grades: clear wind, strong wind and strong wind; Combine the wind speed and the characteristics of the area where the line belongs to early warning to judge the level of short circuit caused by the wind. 9. A wind-induced foreign object short-circuit fault early warning system for power transmission lines, characterized in that it includes: The fault discrimination module is used to collect historical short-circuit image information of foreign objects caused by wind-induced faults, and to distinguish and mark the historical visualization channel images according to faults and non-faults; The feature extraction module is used to sequentially perform grayscale processing, histogram calculation, image enhancement and noise filtering processing on the historical images. The Hough algorithm and the inchworm creep fusion method are used to extract the short-circuit features of foreign objects in the power grid from the processed historical images. According to the short-circuit characteristics of foreign objects in the power grid, a typical wire foreign object comparison library is established; The type division module is used to establish a geographical map of the distribution of hidden dangers in the passage according to the importance of the line, the geographical characteristics and the distribution map of the power grid wind area, and to divide the types of hidden danger areas; The foreign object identification module is used to obtain the real-time visual channel image information of the transmission line, and to identify foreign objects on the real-time visual channel image; The early warning module is used for early warning of foreign objects in the transmission line, and pushes the warning information to the responsible person of the transmission line. 10. The wind-induced foreign object short-circuit fault early warning system for power transmission lines according to claim 9, further comprising: The risk warning module is used to collect the on-site meteorological data of the transmission line, and combine the meteorological data of the meteorological department in the area described by the transmission line to determine the wind speed of the area where the transmission line is located, and set the wind-induced foreign object short-circuit risk warning level according to the meteorological wind speed and surrounding geographical characteristics. .

Images