Substation power equipment state monitoring method and system

Abstract

The invention discloses a substation power equipment state monitoring method and system, and the method comprises the steps: obtaining a visible light image and an infrared image of power equipment, carrying out the image registration and image fusion of the visible light image and the infrared image, and obtaining a power equipment fusion image, and performing defect detection on the fused image of the power equipment according to a preset defect detection model to obtain a final defect result of the power equipment. The structural defects of corrosion, damage and physical damage of the power equipment of the transformer substation and various heating defects can be identified timely and reliably, and an efficient power equipment operation state monitoring means is provided for operation and maintenance personnel.

Description

Technical Field

[0001] The present invention belongs to the technical field of power transmission and transformation equipment operation and inspection, and in particular relates to a method and system for monitoring the status of power equipment in a substation. Background Art

[0002] Since the power equipment in the substation works in the outdoor environment for a long time, it is easy to have structural defects such as corrosion, breakage and physical damage, as well as various heating defects, which seriously affect the safe and stable operation of the power system. Traditional substation power equipment monitoring mostly adopts manual inspection, which consumes a lot of manpower and material resources and lacks timeliness. The rapid progress of artificial intelligence has promoted the widespread application of deep learning target detection models in the power industry. These models have won the recognition of professionals in the power industry for their excellent detection and generalization performance. Therefore, how to apply the target detection model to the monitoring of substation power equipment and design a complete set of convenient and reliable monitoring methods and systems has become an urgent problem to be solved. Summary of the invention

[0003] The present invention provides a method and system for monitoring the status of power equipment in a substation, which are used to solve the technical problem that traditional monitoring of power equipment in a substation mostly adopts a manual inspection mode, which consumes a lot of manpower and material resources and lacks timeliness.

[0004] In a first aspect, the present invention provides a method for monitoring the status of power equipment in a substation, the method comprising: Acquire visible light images and infrared images of power equipment; Performing image registration and image fusion on the visible light image and the infrared image to obtain a fused image of the power equipment; Defect detection is performed on the power equipment fusion image according to a preset defect detection model to obtain a final power equipment defect result, wherein the defect detection model includes a feature extraction network, a feature fusion network and a defect detection network.

[0005] In a second aspect, the present invention provides a substation power equipment status monitoring system, the system comprising: An acquisition module configured to acquire visible light images and infrared images of the electric power equipment; A fusion module, configured to perform image registration and image fusion on the visible light image and the infrared image to obtain a fused image of the power equipment; The detection module is configured to perform defect detection on the power equipment fusion image according to a preset defect detection model to obtain a final power equipment defect result, wherein the defect detection model includes a feature extraction network, a feature fusion network and a defect detection network.

[0006] According to a third aspect, an electronic device is provided, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the steps of the substation power equipment status monitoring method of any embodiment of the present invention.

[0007] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor executes the steps of the substation power equipment status monitoring method of any embodiment of the present invention.

[0008] The substation power equipment status monitoring method and system of the present application obtain visible light images and infrared images of the power equipment, perform image registration and image fusion on the visible light images and infrared images to obtain a fused image of the power equipment, perform defect detection on the fused image of the power equipment according to a preset defect detection model to obtain a final power equipment defect result, and can timely and reliably identify structural defects of corrosion, breakage and physical damage of substation power equipment as well as various types of heating defects, providing operation and maintenance personnel with an efficient means of monitoring the operating status of power equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A flow chart of a method for monitoring the status of power equipment in a substation provided by an embodiment of the present invention; Figure 2 A network structure diagram of a defect detection model provided by an embodiment of the present invention; Figure 3 A specific structural diagram of a defect detection network in a defect detection model provided by an embodiment of the present invention; Figure 4 A structural block diagram of a substation power equipment status monitoring system provided by an embodiment of the present invention; Figure 5 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0011] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0012] See also Figure 1 , which shows a flow chart of a method for monitoring the status of power equipment in a substation of the present application.

[0013] like Figure 1 As shown, the substation power equipment status monitoring method specifically includes the following steps: Step S101, obtaining a visible light image and an infrared image of the power equipment.

[0014] Step S102 , performing image registration and image fusion on the visible light image and the infrared image to obtain a fused image of the power equipment.

[0015] In this step, the LOG operator is used to detect the edges of the visible light image and the infrared image, so as to obtain a first edge image corresponding to the visible light image and a second edge image corresponding to the infrared image; By traversing the point sets in the first edge map and the second edge map, n contours of the power equipment are obtained. Harris corner detector is used to obtain image feature points in the contours. For each image feature point, the nearest point with the local minimum curvature in the contour is searched, which is defined as the left auxiliary feature point and the right auxiliary feature point. The expression is: , , , In the formula, is the left auxiliary feature point, is the right auxiliary feature point, is the first corner point obtained by using Harris corner detector image feature points, is the f-1th image feature point obtained using Harris corner detector, is the f-th image feature point obtained using Harris corner detector, is the f+1th image feature point obtained using Harris corner detector, is the first corner point obtained by using Harris corner detector image feature points, is the left field sampling length, is the right field sampling length, is the normalization constant, is the coordinate of the right auxiliary feature point, is the coordinate of the left auxiliary feature point, is the bilateral filter parameter, Pixel The coordinates of Pixel The coordinates of Pixel The pixel value of Pixel The pixel value of , are the standard deviations of Gaussian functions; A feature triangle is formed based on the image feature point, the left auxiliary feature point and the right auxiliary feature point, a perpendicular line is drawn to the opposite side with the image feature point as the starting point, and the direction of the perpendicular line is defined as the main direction of the feature point; The main direction deviation between the visible light image and the infrared image is The feature points within are considered as a pair of matching points, and lines are drawn between the matching points, and the angles of all lines relative to the horizontal direction are counted; Divide the angles of all lines relative to the horizontal into intervals, take the target angle corresponding to the midpoint of the interval with the largest number of connecting lines and its adjacent intervals, determine the extreme value according to the parabola method and use the target angle as the optimal angle, and deviate from the optimal angle The matching points are defined as mismatched points, and the SIFT feature descriptor is used to perform feature point matching for the mismatched points.

[0016] Furthermore, an image fusion method based on latent low-rank representation decomposes the source image into a low-rank part and a prominent part, and a weighted average strategy is used to fuse the low-rank part to retain more contour information, and a summation strategy is used to fuse the prominent part, and then the fused low-rank part and the fused prominent part are combined to obtain a fused image of the power equipment; Step S103, performing defect detection on the power equipment fusion image according to a preset defect detection model to obtain a final power equipment defect result, wherein the defect detection model includes a feature extraction network, a feature fusion network and a defect detection network.

[0017] In this step, see Figure 2 , the defect detection model includes feature extraction network, feature fusion network and defect detection network. The processing process of feature extraction network is: The fused image of the power equipment is taken as input and sequentially passes through two convolution modules, C2f module, convolution module, C2f module, downsampling module, first PMSC module, downsampling module, second PMSC module, pooling module and attention module; Among them, the outputs of the C2f module, the first PMSC module, and the attention module, which are all connected to the feature fusion network, are respectively the first output result N1, the second output result N2, the third output result N3, and the fourth output result N4.

[0018] Among them, the processing process of the feature fusion network is: The third output result N3 is input into the splicing module together with the second output result N2 after passing through the upsampling module for feature fusion; The output of the splicing module is then passed through the third PMSC module, and the output of the third PMSC module is the fifth output result N5 and the sixth output result N6; The fifth output result N5 is input into the splicing module together with the first output result N1 for feature fusion after passing through the upsampling module. The output of the splicing module is then input into the C2f module. The output of the C2f module is the seventh output result N7 and the eighth output result N8. The seventh output result N7 is input into the detection module for defect detection of substation equipment, and the eighth output result N8 is input into the splicing module together with the sixth output result N6 after passing through the convolution module for feature fusion, and the output of the splicing module is then input into the fourth PMSC module, and the output of the fourth PMSC module is the ninth output result N9 and the tenth output result N10; The ninth output result N9 is input into the detection module for substation equipment defect detection, and the tenth output result N10 is input into the splicing module together with the fourth output result N4 for feature fusion after passing through the downsampling module. The output of the splicing module passes through the fifth PMSC module to obtain the eleventh output result N11, and the eleventh output result N11 is input into the detection module for substation equipment defect detection.

[0019] The specific processing process of the downsampling module in the defect detection model includes: For the input 192×80×60 image, the image size is first adjusted to 384×80×60 by a 1×1 point-by-point convolution with a convolution kernel of 1 and a stride of 1, and then the image size is spatially downsampled to 384×40×30 by a 3×3 depthwise convolution with a convolution kernel of 3 and a stride of 2.

[0020] The specific processing process of the attention module in the defect detection model includes: The input image is first subjected to a 1×1 point-by-point convolution with a convolution kernel of 1 and a stride of 1, and then divided into two parts according to the number of channels. One part is processed by the MSHA multi-dimensional information attention mechanism and multi-layer perception, connected to the other part through a splicing module, and then subjected to a 1×1 convolution with a convolution kernel of 1 and a stride of 1 before being output.

[0021] The specific processing process of the PMSC module in the defect detection model includes: The input feature map is divided into three parts according to the ratio of 50%, 25% and 25%. One part of 25% is output through a 1×1 convolution with a convolution kernel of 1, and the other part of 25% is output through a 3×3 convolution with a convolution kernel of 3. The two outputs and the split 50% feature map are Figure 1 The features of each channel are fused together by inputting them into the concatenation module and a 1×1 point-by-point convolution.

[0022] See also Figure 3 , the processing of the defect detection network includes: The seventh output result N7, the ninth output result N9 and the eleventh output result N11 are used as the input of the defect detection network. They are first subjected to a 1×1 convolution with a convolution kernel of 1 to adjust the number of channels, and then a 3×3 convolution module is shared to share the convolution weights to obtain the seventh target output result. 、9th target output result And the eleventh target output result ; Output the result of the seventh goal 、The ninth goal outputs the result And the eleventh target output result They pass through a BS module, a regression convolution module and a classification convolution module respectively, where the BS module includes a BN layer and a Silu activation function layer.

[0023] In summary, the method of the present application obtains visible light images and infrared images of power equipment, performs image registration and image fusion on the visible light images and infrared images to obtain a fused image of the power equipment, performs defect detection on the fused image of the power equipment according to a preset defect detection model, and obtains the final power equipment defect result. It can timely and reliably identify structural defects such as corrosion, breakage and physical damage of substation power equipment and various types of heating defects, and provide operation and maintenance personnel with an efficient means of monitoring the operating status of power equipment.

[0024] In a specific embodiment, the substation power equipment status monitoring method is used in a power equipment status monitoring system, the power equipment status monitoring system includes an IoT integrated management platform, a switch, an intelligent diagnostic device, and a thermal imaging binocular gimbal, and the method specifically includes the following steps: The IoT integrated management platform creates power equipment status monitoring tasks according to the daily inspection needs of substations, and sends the tasks to the thermal imaging binocular gimbal through the switch; After receiving the task from the IoT integrated management platform, the thermal imaging binocular gimbal rotates the binocular gimbal to the preset position, captures visible light and infrared images of the power equipment in the monitoring area, and sends the visible light and infrared images of the power equipment to the intelligent diagnostic device; After receiving the image, the intelligent diagnostic device performs image registration and image fusion on the visible light image and infrared image of the power equipment to obtain a fused image of the power equipment. The defect detection module then detects the equipment defects in the fused image and transmits the defect detection results back to the thermal imaging binocular gimbal. The defect detection module includes a feature extraction network, a feature fusion network, and a defect detection network. After the thermal imaging binocular gimbal receives the defect detection results of the power equipment, it reports the image code stream and alarm information to the IoT integrated management platform. The power operation and maintenance personnel will issue further equipment monitoring tasks and decide whether the equipment needs to be repaired.

[0025] See also Figure 4 , which shows a structural block diagram of a substation power equipment status monitoring system of the present application.

[0026] like Figure 4 As shown, the substation power equipment status monitoring system 200 includes an acquisition module 210 , a fusion module 220 and a detection module 230 .

[0027] Among them, the acquisition module 210 is configured to acquire the visible light image and the infrared image of the power equipment; the fusion module 220 is configured to perform image registration and image fusion on the visible light image and the infrared image to obtain the fused image of the power equipment; the detection module 230 is configured to perform defect detection on the fused image of the power equipment according to a preset defect detection model to obtain the final defect result of the power equipment, wherein the defect detection model includes a feature extraction network, a feature fusion network and a defect detection network.

[0028] It should be understood that Figure 4 Modules and references documented in Figure 1 Therefore, the operations and features described above for the method and the corresponding technical effects are also applicable to Figure 4 The modules in it will not be described in detail here.

[0029] In some other embodiments, the embodiments of the present invention further provide a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor is caused to execute the substation power equipment status monitoring method in any of the above method embodiments; As an implementation mode, the computer-readable storage medium of the present invention stores computer-executable instructions, and the computer-executable instructions are configured as follows: Acquire visible light images and infrared images of power equipment; Performing image registration and image fusion on the visible light image and the infrared image to obtain a fused image of the power equipment; Defect detection is performed on the power equipment fusion image according to a preset defect detection model to obtain a final power equipment defect result, wherein the defect detection model includes a feature extraction network, a feature fusion network and a defect detection network.

[0030] The computer-readable storage medium may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required by at least one function; the data storage area may store data created according to the use of the substation power equipment status monitoring system, etc. In addition, the computer-readable storage medium may include a high-speed random access memory, and may also include a memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer-readable storage medium may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the substation power equipment status monitoring system via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0031] Figure 5 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 5 As shown, the device includes: a processor 310 and a memory 320. The electronic device may also include: an input device 330 and an output device 340. The processor 310, the memory 320, the input device 330 and the output device 340 may be connected via a bus or other means. Figure 5 In the example, the bus connection is used. The memory 320 is the above-mentioned computer-readable storage medium. The processor 310 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 320, that is, the substation power equipment status monitoring method of the above-mentioned method embodiment is realized. The input device 330 can receive input digital or character information, and generate key signal input related to user settings and function control of the substation power equipment status monitoring system. The output device 340 may include display devices such as display screens.

[0032] The electronic device can execute the method provided by the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not described in detail in this embodiment, please refer to the method provided by the embodiment of the present invention.

[0033] As an implementation mode, the electronic device is applied to a substation power equipment status monitoring system, and is used for a client, and includes: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can: Acquire visible light images and infrared images of power equipment; Performing image registration and image fusion on the visible light image and the infrared image to obtain a fused image of the power equipment; Defect detection is performed on the power equipment fusion image according to a preset defect detection model to obtain a final power equipment defect result, wherein the defect detection model includes a feature extraction network, a feature fusion network and a defect detection network.

[0034] Through the description of the above implementation modes, those skilled in the art can clearly understand that each implementation mode can be implemented by means of software plus a necessary general hardware platform, or of course by hardware. Based on such an understanding, the above technical solution can essentially or in other words be embodied in the form of a software product that contributes to the prior art. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0035] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for monitoring the status of power equipment in a substation, characterized in that: The method comprises: Acquire visible light images and infrared images of power equipment; Performing image registration and image fusion on the visible light image and the infrared image to obtain a fused image of the power equipment; Defect detection is performed on the power equipment fusion image according to a preset defect detection model to obtain a final power equipment defect result, wherein the defect detection model includes a feature extraction network, a feature fusion network and a defect detection network.

2. A method for monitoring the status of power equipment in a substation according to claim 1, characterized in that: in, Performing image registration on the visible light image and the infrared image specifically includes: Using a LOG operator to detect edges of the visible light image and the infrared image, to obtain a first edge image corresponding to the visible light image and a second edge image corresponding to the infrared image; By traversing the point sets in the first edge map and the second edge map, n contours of the power equipment are obtained. Harris corner detector is used to obtain image feature points in the contours. For each image feature point, the nearest point with the local minimum curvature in the contour is searched, which is defined as the left auxiliary feature point and the right auxiliary feature point. The expression is: ， ， ， In the formula, is the left auxiliary feature point, is the right auxiliary feature point, is the first corner point obtained by using Harris corner detector image feature points, is the f-1th image feature point obtained using Harris corner detector, is the f-th image feature point obtained using Harris corner detector, is the f+1th image feature point obtained using Harris corner detector, is the first corner point obtained by using Harris corner detector image feature points, is the left field sampling length, is the right field sampling length, is the normalization constant, is the coordinate of the right auxiliary feature point, is the coordinate of the left auxiliary feature point, is the bilateral filter parameter, Pixel The coordinates of Pixel The coordinates of Pixel The pixel value of Pixel The pixel value of , are the standard deviations of Gaussian functions; A feature triangle is formed based on the image feature point, the left auxiliary feature point and the right auxiliary feature point, a perpendicular line is drawn to the opposite side with the image feature point as the starting point, and the direction of the perpendicular line is defined as the main direction of the feature point; The main direction deviation between the visible light image and the infrared image is The feature points within are considered as a pair of matching points, and lines are drawn between the matching points, and the angles of all lines relative to the horizontal direction are counted; Divide the angles of all lines relative to the horizontal into intervals, take the target angle corresponding to the midpoint of the interval with the largest number of connecting lines and its adjacent intervals, determine the extreme value according to the parabola method and use the target angle as the optimal angle, and deviate from the optimal angle The matching points are defined as mismatched points, and the SIFT feature descriptor is used to perform feature point matching for the mismatched points.

3. A method for monitoring the status of power equipment in a substation according to claim 1, characterized in that: in, The processing process of the feature extraction network is: The fused image of the power equipment is taken as input and sequentially passes through two convolution modules, a C2f module, a downsampling module, a first PMSC module, a downsampling module, a second PMSC module, a pooling module, and an attention module; Among them, the outputs of the C2f module, the first PMSC module, and the attention module, which are all connected to the feature fusion network, are respectively the first output result N1, the second output result N2, the third output result N3, and the fourth output result N4.

4. A method for monitoring the status of power equipment in a substation according to claim 3, characterized in that: in, The processing process of the feature fusion network is: The third output result N3 is input into the splicing module together with the second output result N2 after passing through the upsampling module for feature fusion; The output of the splicing module is then passed through the third PMSC module, and the output of the third PMSC module is the fifth output result N5 and the sixth output result N6; The fifth output result N5 is input into the splicing module together with the first output result N1 for feature fusion after passing through the upsampling module. The output of the splicing module is then input into the C2f module. The output of the C2f module is the seventh output result N7 and the eighth output result N8. The seventh output result N7 is input into the detection module for defect detection of substation equipment, and the eighth output result N8 is input into the splicing module together with the sixth output result N6 after passing through the convolution module for feature fusion, and the output of the splicing module is then input into the fourth PMSC module, and the output of the fourth PMSC module is the ninth output result N9 and the tenth output result N10; The ninth output result N9 is input into the detection module for substation equipment defect detection, and the tenth output result N10 is input into the splicing module together with the fourth output result N4 for feature fusion after passing through the downsampling module. The output of the splicing module passes through the fifth PMSC module to obtain the eleventh output result N11, and the eleventh output result N11 is input into the detection module for substation equipment defect detection.

5. A method for monitoring the status of power equipment in a substation according to claim 1, characterized in that: in, The specific processing process of the downsampling module in the defect detection model includes: For the input 192×80×60 image, the image size is first adjusted to 384×80×60 by a 1×1 point-by-point convolution with a convolution kernel of 1 and a stride of 1, and then the image size is spatially downsampled to 384×40×30 by a 3×3 depthwise convolution with a convolution kernel of 3 and a stride of 2.

6. A method for monitoring the status of power equipment in a substation according to claim 1, characterized in that: in, The specific processing process of the attention module in the defect detection model includes: The input image is first subjected to a 1×1 point-by-point convolution with a convolution kernel of 1 and a stride of 1, and then divided into two parts according to the number of channels. One part is processed by the MSHA multi-dimensional information attention mechanism and multi-layer perception, connected to the other part through a splicing module, and then subjected to a 1×1 convolution with a convolution kernel of 1 and a stride of 1 before being output.

7. A method for monitoring the status of power equipment in a substation according to claim 1, characterized in that: in, The specific processing process of the PMSC module in the defect detection model includes: The input feature map is divided into three parts according to the ratio of 50%, 25% and 25%. One part of 25% is output through a 1×1 convolution with a convolution kernel of 1, and the other part of 25% is output through a 3×3 convolution with a convolution kernel of 3. The two outputs and the 50% feature map are input into the splicing module and a 1×1 point-by-point convolution to fuse the features of each channel.

8. A method for monitoring the status of power equipment in a substation according to claim 1, characterized in that: The processing of the defect detection network includes: The seventh output result N7, the ninth output result N9 and the eleventh output result N11 are used as the input of the defect detection network. They are first subjected to a 1×1 convolution with a convolution kernel of 1 to adjust the number of channels, and then a 3×3 convolution module is shared to share the convolution weights to obtain the seventh target output result. 、9th target output result And the eleventh target output result ; Output the result of the seventh goal 、9th target output result And the eleventh target output result They pass through a BS module, a regression convolution module and a classification convolution module respectively, where the BS module includes a BN layer and a Silu activation function layer.

9. A substation power equipment status monitoring system, characterized in that: The system comprises: An acquisition module configured to acquire visible light images and infrared images of the electric power equipment; A fusion module, configured to perform image registration and image fusion on the visible light image and the infrared image to obtain a fused image of the power equipment; The detection module is configured to perform defect detection on the power equipment fusion image according to a preset defect detection model to obtain a final power equipment defect result, wherein the defect detection model includes a feature extraction network, a feature fusion network and a defect detection network.

Images