A control method and system for the monitoring period of a transmission line monitoring device

Abstract

The present invention belongs to the technical field of monitoring device control, and provides a control method and system for the monitoring period of transmission line monitoring devices. First, meteorological data and season data are obtained; then, scene data is obtained according to the scene acquisition method. If the scene acquisition method is entry, the entered scene data is obtained, otherwise, a monitoring image is obtained, and the scene data is obtained by means of image recognition; based on the meteorological data, season data and scene data, the hidden danger level is judged according to the preset level judgment rule; finally, the monitoring period of the monitoring device is adjusted based on the hidden danger level; it solves the resource waste caused by the unified parameter setting of existing monitoring devices, and realizes the automatic adjustment of the image capture interval according to the severity of the hidden danger.

Description

Technical Field

[0001] The present invention belongs to the technical field of monitoring equipment control, and in particular relates to a control method and system for a monitoring cycle of a power transmission line monitoring equipment. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Currently, visual monitoring equipment has been widely used in power transmission and distribution lines, playing an increasingly important role in channel external force protection. Existing image visual monitoring equipment generally acquires channel images at regular intervals, and then transmits the images back to the server through the power network, thereby intelligently identifying hidden dangers of construction machinery such as cranes and excavators.

[0004] However, with the increase in visual monitoring equipment, the pressure on servers such as image storage and intelligent recognition is increasing, and the large-scale image transmission has also increased traffic costs. Summary of the invention

[0005] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides a control method and system for the monitoring cycle of power transmission line monitoring equipment. Different monitoring cycles are set according to different scene data, and can be automatically adjusted with the climate and season, so as to give full play to the role of the monitoring device, solve the waste of resources caused by the unified parameter setting of the existing monitoring equipment, and realize the automatic adjustment of the image capture interval according to the severity of the hidden danger.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] A first aspect of the present invention provides a method for controlling a monitoring cycle of a power transmission line monitoring device, comprising:

[0008] Get weather and seasonal data;

[0009] Determine the scene acquisition method and obtain the scene data; specifically: if the scene acquisition method is input, obtain the input scene data; otherwise, obtain the monitoring image and obtain the scene data by image recognition method;

[0010] Based on meteorological data, seasonal data and scenario data, the hidden danger level is judged according to the preset level judgment rules;

[0011] Adjust the monitoring cycle of monitoring equipment based on the level of hidden dangers.

[0012] Furthermore, the preset level judgment rules vary according to different ways of obtaining hidden danger scenarios, specifically:

[0013] If the hidden danger scene acquisition method is input, the level judgment rule adopts the first level judgment rule;

[0014] If the hidden danger scene data is the hidden danger scene data obtained by an image recognition method, the level judgment rule adopts the second level judgment rule.

[0015] Furthermore, the specific steps of the image recognition method are:

[0016] Performing grayscale processing on the monitoring image to obtain a grayscale image;

[0017] Divide the grayscale image into multiple sub-regions based on clustering algorithm;

[0018] The sub-region is input into the ResNet model, feature information is extracted, the scene of the sub-region is identified, and the scene data included in the monitoring image is obtained.

[0019] Furthermore, the specific steps of dividing the grayscale image into multiple sub-areas based on the clustering algorithm are:

[0020] Step 1: Calculate the initial membership between the pixel points in the grayscale image and the initial cluster center;

[0021] Step 2: Update the membership degree between the pixel point and the cluster center and the pixel value of the cluster center;

[0022] Step 3: Determine whether the end condition is met. If so, the membership degree between the pixel point and the cluster center is obtained, the iteration ends, and the next step is entered; otherwise, return to step 2;

[0023] Step 4: Based on the membership of the pixel points and the cluster center, the pixel points in the grayscale image are divided into different categories to obtain multiple sub-regions.

[0024] Furthermore, the specific steps of updating the membership degree of the pixel point to the cluster center and the pixel value of the cluster center are:

[0025] Calculate the similarity between the neighborhood where the pixel point is located and the cluster center based on the membership degree;

[0026] Based on the similarity between the neighborhood of the pixel point and the cluster center, the similarity between the pixel point and the cluster center is calculated;

[0027] Based on the similarity between the pixel point and the cluster center, the membership degree of the pixel point and the cluster center and the pixel value of the cluster center are calculated.

[0028] Furthermore, the termination condition is that the number of iterations is greater than the maximum number of iterations, or the difference between the objective function of this iteration and the objective function of the previous iteration is less than or equal to the termination threshold.

[0029] A second aspect of the present invention provides a control system for a monitoring cycle of a power transmission line monitoring device, comprising:

[0030] A meteorological and seasonal data acquisition module, which is configured to: acquire meteorological data and seasonal data;

[0031] The scene data acquisition module is configured to: determine the scene acquisition method and acquire the scene data; specifically: if the scene acquisition method is input, then acquire the input scene data; otherwise, acquire the monitoring image and acquire the scene data by image recognition method;

[0032] A hidden danger level judgment module is configured to: judge the hidden danger level according to preset level judgment rules based on meteorological data, seasonal data and scene data;

[0033] The monitoring cycle adjustment module is configured to adjust the monitoring cycle of the monitoring equipment based on the hidden danger level.

[0034] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the method for controlling the monitoring cycle of a power transmission line monitoring device as described above.

[0035] The fourth aspect of the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the control method of the monitoring cycle of a power transmission line monitoring device as described above are implemented.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] The present invention provides a control method for the monitoring cycle of a power transmission line monitoring device. Different monitoring cycles are set according to different scene data, and the monitoring cycles can be automatically adjusted with the climate and season, so as to give full play to the role of the monitoring device, solve the resource waste caused by the unified parameter setting of the existing monitoring equipment, and realize the automatic adjustment of the image capture interval according to the severity of the hidden danger.

[0038] The present invention provides a control method for the monitoring cycle of a power transmission line monitoring device. When performing image segmentation, an FCM algorithm with a neighborhood is adopted to solve the problem that the fuzzy C-means clustering algorithm is sensitive to noise and has a poor processing effect on noisy images. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0040] Figure 1The present invention is a flowchart of a method for controlling a monitoring cycle of a power transmission line monitoring device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0042] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0043] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0044] Embodiment 1

[0045] like Figure 1 As shown, this embodiment provides a method for controlling the monitoring cycle of a power transmission line monitoring device, which specifically includes the following steps:

[0046] Step 1: Get weather data and seasonal data.

[0047] Among them, meteorological data is obtained through meteorological stations or micro-meteorological devices, and seasonal data is obtained through seasonal detection devices.

[0048] Meteorological data includes strong winds (blue, orange, and red warnings), heavy rain, heavy snow, etc.

[0049] Seasonal data include the autumn harvest season (September-October), tomb-visiting season (the 15th day of the first lunar month, Qingming Festival, Zhongyuan Festival, Cold Food Festival, New Year's Eve, the third day of the first lunar month, etc.), flood season (July-September), etc. Different regions can adjust seasonal parameters appropriately according to different situations.

[0050] Step 2: Determine the scene acquisition method and obtain the scene data; specifically: if the scene acquisition method is input, obtain the input scene data and use it as the scene data; otherwise, obtain the monitoring image and obtain the scene data through image recognition method.

[0051] As an implementation method, the staff enters the scene acquisition method in the terminal, and the scene acquisition method includes entry and autonomous acquisition methods: if the scene acquisition method is entry, the staff enters the scene data through the terminal within a preset time period (the last day of each quarter or the day when the monitoring equipment is installed on the transmission line) and uses it as the scene data; if the scene acquisition method is autonomous acquisition, the monitoring equipment obtains multiple monitoring images within a preset time period (the last day of each quarter or the day when the monitoring equipment is installed on the transmission line) and obtains the scene data through image recognition methods.

[0052] The specific method of obtaining the input scene data is as follows: the staff judges the scene where the transmission line monitoring equipment is located within the preset time period and enters the scene data through the terminal device. The channels of the transmission line are divided in detail according to the scene classification principle. For the convenience of input, as shown in Table 1, the detailed hidden danger scenes are coded. The staff only needs to enter the scene data related codes through the terminal device. For example, the code WP21B1 represents the construction external damage prone area (WP)-occasional construction point (2)-underline (1)-crane construction (B1). The monitoring equipment of each line channel corresponds to a code.

[0053] The scene data is obtained through image recognition methods, specifically:

[0054] (1) grayscale the monitoring image to obtain a grayscale image;

[0055] (2) Divide the grayscale image into multiple sub-regions based on the clustering algorithm:

[0056] As an implementation method, the clustering algorithm adopts the FCM algorithm with the neighborhood introduced. The specific steps of the FCM algorithm with the neighborhood introduced include:

[0057] (2-1) Determine the number of sub-regions K and the pixel values ​​of the K initial cluster centers (c 1 ,c 2 ,…,c K ), membership factor, similarity threshold, end threshold ξ and maximum number of iterations T.

[0058] (2-2) Calculate the initial membership u of pixel point j in the grayscale image and the initial cluster center i ij

[0059]

[0060] Among them, x j is the gray value of pixel j, c i is the gray value of cluster center i, m is the membership factor, and K is the number of cluster centers, that is, the number of sub-regions.

[0061] (2-3) Based on the membership degree u ij Calculate the similarity between the neighborhood of pixel point j and cluster center i, specifically:

[0062] If the membership degree u between the pth pixel in the neighborhood of pixel j and cluster center i is ij is greater than the similarity threshold α, then the parameter M i The value of plus 1, that is, parameter M i It is used to count the number of pixels in the neighborhood where pixel j is located and whose similarity with cluster center i is greater than the similarity threshold α. Then the similarity between the neighborhood where pixel j is located and cluster center i is

[0063]

[0064] Among them, M is the total number of pixels in the neighborhood of pixel j.

[0065] (2-4) Combine the similarity between the neighborhood of pixel j and cluster center i to calculate the similarity d between pixel j and cluster center i ij

[0066] d ij =|x j -c i |p ij

[0067] (2-5) Based on the similarity d between pixel j and cluster center i ij , update the membership u of pixel j and cluster center i ij and the pixel value c of the cluster center i :

[0068]

[0069]

[0070] Where N is the total number of pixels in the grayscale image.

[0071] (2-7) Calculate the objective function:

[0072]

[0073] (2-8) Determine whether the end condition is met. If so, obtain the membership degree u between pixel point j and cluster center i ij , the iteration ends and goes to the next step; otherwise, the number of iterations t is increased by 1, and the process returns to step (2-3) to continue iterating. The end condition is that the number of iterations is greater than the maximum number of iterations, or the difference between the objective function of this iteration and the objective function of the previous iteration is less than or equal to the end threshold, that is, |J t -J t-1|≤ξor t>T.

[0074] (2-9) Based on the membership degree u ij , divide the pixels in the grayscale image into different categories and obtain multiple sub-regions.

[0075] (3) Input the sub-region into the ResNet model, extract feature information, identify the scene of the sub-region, and obtain all scene data included in the monitoring image (scene data includes hidden danger scenes and non-hidden danger scenes. Hidden danger scenes include: rivers, river banks; fields; forests; railways, highways and other important roads; tower cranes, excavators, dump trucks and other large construction vehicles; plastic greenhouses, dust-proof nets, ground films, reflective films, color steel tiles and other easy-to-float objects). For specific steps, please refer to Chinese Patent 202110346316.6 Garbage classification method and garbage classifier based on multi-label image recognition.

[0076] Step 3: Based on the acquired meteorological data, seasonal data and scenario data, the hidden danger level is determined according to the preset level judgment rules;

[0077] Among them, the preset level judgment rules vary according to the different ways of obtaining the scene data. Specifically: if the scene data is input scene data, the level judgment rules adopt the first-level judgment rules; if the scene data is scene data obtained by image recognition method, the level judgment rules adopt the second-level judgment rules.

[0078] After the staff inputs the code of the hidden danger scene, the first-level judgment rule is used for the grade judgment rule. The first-level judgment rule includes five hidden danger levels (special, first, second, third, and fourth). The channel scenes under different hidden danger categories are matched and divided according to the construction category, hidden danger nature, climate, season and other factors. The division rules of special, first, second and third levels are shown in Table 1. The scenes that do not belong to special, first, second and third levels are divided into fourth level. Table 1 shows that the transmission channel is divided into eight major hidden danger categories according to the hidden danger category, including "three spans" and important spans, construction external damage prone areas, floating objects prone areas, channel bamboo and wood prone areas, forest fire prone areas, river sections, natural disaster prone areas, and other sections. Each major hidden danger category is refined to form medium and small categories.

[0079] For example, the staff enters the scenario code SK4B1, which represents "three spans" and important spans (SK) - other important spans (4) - across rural roads (B1). If the seasonal data at this time is the autumn harvest season, the hidden danger level is level 1, otherwise it is level 4. The code for the scenario that does not belong to the hidden danger scenario in Table 1 is FN.

[0080]

[0081]

[0082]

[0083] If the scene data is obtained by image recognition, the level judgment rule adopts the second-level judgment rule; the second-level judgment rule is specifically:

[0084] If the scene data of the monitoring image includes two or more potential hazard scenes (for example, both forests and railways); or, the scene data of the monitoring image only includes large construction vehicles such as tower cranes, excavators, and dump trucks; or, the meteorological data is heavy snow, strong wind, heavy rain, strong wind or heavy rain; or, the scene data of the monitoring image only includes plastic greenhouses, dust-proof nets, ground films, reflective films, color steel tiles and other easy-to-float objects; then, the potential hazard level is special grade;

[0085] If the scene data of the monitoring image only includes important roads such as railways and highways; or the scene data of the monitoring image only includes rivers, and the season data belongs to the flood season; or the scene data of the monitoring image only includes fields, and the season data belongs to autumn harvest; or the scene data of the monitoring image only includes mountains and forests, and the season data belongs to the tomb-visiting season; then the hidden danger level is level one;

[0086] If the scene data of the monitoring image only includes the river channel; or the scene data of the monitoring image only includes the river bank, and the seasonal data belongs to the flood season; then, the hidden danger level is level 2;

[0087] If,the scene data of the monitoring image only includes riverbanks or fields,,the hidden danger level is level three;

[0088] The remaining scenes are level four.

[0089] Step 4: Adjust the monitoring cycle of the monitoring equipment based on the level of hidden dangers.

[0090] As an implementation method, the higher the level (special level > level one > level two > level three > level four), the shorter the interval period of the monitoring device's surveillance.

[0091] The method of the present invention can automatically adjust the hidden danger level according to the channel hidden danger category, climate, and season, thereby realizing automatic adjustment of the monitoring cycle of the monitoring equipment and realizing environmental self-matching adjustment of the monitoring equipment, and is suitable for the intelligent management of power transmission visualization monitoring equipment of power supply companies in various cities.

[0092] The method of the present invention can set different monitoring cycles according to different scene data, and can automatically adjust with the climate and season, giving full play to the role of the monitoring device, solving the resource waste caused by the unified parameter setting of existing monitoring equipment, and realizing automatic adjustment of the image capture interval according to the severity of hidden dangers.

[0093] Embodiment 2

[0094] This embodiment provides a control system for a monitoring cycle of a power transmission line monitoring device, which specifically includes the following modules:

[0095] A meteorological and seasonal data acquisition module, which is configured to: acquire meteorological data and seasonal data;

[0096] The scene data acquisition module is configured to: determine the scene acquisition method and acquire the scene data; specifically: if the scene acquisition method is input, then acquire the input scene data; otherwise, acquire the monitoring image and acquire the scene data by image recognition method;

[0097] A hidden danger level judgment module is connected to the scene data acquisition module and the monitoring device, and is configured to: judge the hidden danger level according to preset level judgment rules based on meteorological data, seasonal data and scene data;

[0098] The monitoring cycle adjustment module is configured to adjust the monitoring cycle of the monitoring equipment based on the hidden danger level.

[0099] The terminal device is connected to the scene data acquisition module and is used for the user to enter the scene acquisition method and scene data.

[0100] The monitoring device is also connected to the scene data acquisition module for acquiring monitoring images.

[0101] The meteorological and seasonal data acquisition module is a meteorological station and a seasonal detection device.

[0102] It should be noted here that each module in this embodiment corresponds to each step in Example 1 one by one, and the specific implementation process is the same, which will not be repeated here.

[0103] Embodiment 3

[0104] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps in the method for controlling the monitoring cycle of a power transmission line monitoring device as described in the first embodiment above are implemented.

[0105] Embodiment 4

[0106] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the method for controlling the monitoring cycle of a power transmission line monitoring device as described in the first embodiment above are implemented.

[0107] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0108] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0109] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0110] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0111] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0112] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A control method for the monitoring period of a transmission line monitoring device, characterized in that, it includes: Obtain meteorological data and season data; Determine the scene acquisition method and obtain scene data; specifically: if the scene acquisition method is entry, obtain the entered scene data; otherwise, obtain the monitoring image and obtain the scene data by means of image recognition; Based on the meteorological data, season data and scene data, judge the hidden danger level according to the preset level judgment rule; the preset level judgment rule is different according to the different hidden danger scene acquisition methods, specifically: If the hidden danger scene acquisition method is entry, the level judgment rule adopts the first-level judgment rule; If the hidden danger scene acquisition method is obtained by means of image recognition, the level judgment rule adopts the second-level judgment rule; Adjust the monitoring period of the monitoring device based on the hidden danger level.

2. The control method for the monitoring period of a transmission line monitoring device according to claim 1, characterized in that, The specific steps of the image recognition method are: Perform grayscale processing on the monitoring image to obtain a grayscale image; Divide the grayscale image into multiple sub-regions based on the clustering algorithm; Input the sub-regions into the ResNet model, extract feature information, identify the scenes of the sub-regions, and obtain the scene data included in the monitoring image.

3. The control method for the monitoring period of a transmission line monitoring device according to claim 2, characterized in that, The specific steps of dividing the grayscale image into multiple sub-regions based on the clustering algorithm are: Step 1: Calculate the initial membership degree of the pixel points in the grayscale image to the initial clustering centers; Step 2: Update the membership degree of the pixel points to the clustering centers and the pixel values of the clustering centers; Step 3: Judge whether the end condition is satisfied. If it is satisfied, obtain the membership degree of the pixel points to the clustering centers, the iteration ends, and enter the next step; Otherwise, return to Step 2; Step 4: Based on the membership degree of the pixel points to the clustering centers, divide the pixel points in the grayscale image into different categories to obtain multiple sub-regions.

4. The control method for the monitoring period of a transmission line monitoring device according to claim 3, characterized in that, The specific steps of updating the membership degree of the pixel points to the clustering centers and the pixel values of the clustering centers are: Calculate the similarity between the neighborhood where the pixel point is located and the clustering center based on the membership degree; Calculate the similarity between the pixel point and the clustering center based on the similarity between the neighborhood where the pixel point is located and the clustering center; Calculate the membership degree of the pixel point to the clustering center and the pixel value of the clustering center based on the similarity between the pixel point and the clustering center.

5. The control method for the monitoring period of a transmission line monitoring device according to claim 3, characterized in that, The end condition is that the number of iterations is greater than the maximum number of iterations, or the difference between the objective function of this iteration and the objective function of the previous iteration is less than or equal to the end threshold.

6. A control system for the monitoring period of a transmission line monitoring device, characterized in that, it includes: A meteorological and season data acquisition module, which is configured to: obtain meteorological data and season data; A scene data acquisition module, which is configured to: determine a scene acquisition method and acquire scene data; specifically: if the scene acquisition method is entry, acquire the entered scene data; otherwise, acquire a monitoring image and acquire scene data by means of image recognition; A hidden danger level judgment module, which is configured to: based on meteorological data, seasonal data and scene data, judge the hidden danger level according to a preset level judgment rule; the preset level judgment rule is different according to different hidden danger scene acquisition methods, specifically: If the hidden danger scene acquisition method is entry, the level judgment rule adopts the first-level judgment rule; If the hidden danger scene acquisition method is acquired by means of image recognition, the level judgment rule adopts the second-level judgment rule; A monitoring period adjustment module, which is configured to: adjust the monitoring period of the monitoring device based on the hidden danger level.

7. A computer-readable storage medium, on which a computer program is stored, characterized in that, when the program is executed by a processor, it implements the steps in a control method for the monitoring period of a transmission line monitoring device as described in any one of claims 1-5.

8. A computer device, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that, when the processor executes the program, it implements the steps in a control method for the monitoring period of a transmission line monitoring device as described in any one of claims 1-5.

Images