Method and device for removing bird nests from high-voltage switchgear mechanisms of a substation
By combining image recognition and multispectral technology with a puncture mechanism, the bird's nest on the high-voltage switch mechanism of the substation can be accurately removed, solving the high safety risk problem in the existing technology, especially the removal of bird's nests in semi-enclosed areas, and improving the safety and efficiency of operations.
Patent Information
- Application Number
- CN202511021483.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-24
- Publication Date
- 2025-10-21
- Estimated Expiration
- 2045-07-24
AI Technical Summary
In the prior art, the removal of bird nests on the high-voltage switch mechanism of a substation relies on manual operation, which poses high safety risks and potential tripping accidents. It is particularly difficult to remove bird nests in semi-enclosed areas.
By acquiring visible light images from the high-voltage knife mechanism, the shape of the area where the bird's nest is located is determined using image recognition technology, and the safe removal device is controlled for precise removal. This includes using multispectral and ultrasonic images to identify nesting material information, combined with the umbrella net structure of the puncture mechanism to remove the bird's nest.
It has achieved precise removal of bird nests on the high-voltage switch mechanism of the substation, especially the bird nests in the semi-enclosed area, reducing the safety risks during the removal process and improving the safety and efficiency of operations.
Smart Images

Figure CN120526359B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of equipment control technology, and in particular to a method and device for removing bird nests on a high-voltage switch mechanism of a substation. Background Art
[0002] Knife switches (also known as disconnectors) are switching devices primarily used to isolate power sources and lack arc extinguishing capabilities. They are widely deployed in substations. Since many substations are built outdoors, birds frequently nest in high-voltage knife switches, creating a series of safety risks.
[0003] In the prior art, maintenance personnel typically use tools such as insulated rods to remove bird nests from high-voltage switch mechanisms during routine maintenance of substations. However, this relies on visual judgment by maintenance personnel, and the removal process can cause tripping accidents, posing a high risk of accidents. Summary of the Invention
[0004] In order to solve the above technical problems, the embodiment of the present application proposes a method and device for removing bird nests on the high-voltage knife switch mechanism of the substation, which can accurately remove bird nests on the high-voltage knife switch mechanism of the substation, especially the bird nests in the semi-enclosed area, thereby reducing the safety risks during the bird nest removal process.
[0005] In a first aspect, an embodiment of the present application provides a method for removing a bird's nest on a high-voltage switch mechanism of a substation, comprising:
[0006] Acquire a visible light image corresponding to the high-voltage switch mechanism of the substation;
[0007] performing image recognition on the visible light image, and determining, based on the image recognition result, a morphology of the area where the bird's nest is located, wherein the morphology of the area where the bird's nest is located includes an open area or a semi-enclosed area. If the visible light image includes a hole image, the hole image includes a hole and a portion of the bird's nest observed through the hole. The image recognition result includes a second nest boundary of the portion of the nest detected in the hole image and a hole boundary of the hole. If an overlap rate is greater than a preset overlap rate threshold, determining that the morphology of the area where the bird's nest is located is a semi-enclosed area, the overlap rate being determined based on the second nest boundary and the hole boundary.
[0008] In a case where the area where the bird's nest is located is a semi-enclosed area, a safety clearing device is controlled to clear the bird's nest based on the visible light image.
[0009] Optionally, the visible light image includes images from multiple perspectives, and performing image recognition on the visible light image and determining the shape of the area where the bird's nest is located according to the image recognition result includes:
[0010] performing edge detection on each of the images from the multiple perspectives to obtain a first bird's nest boundary of the bird's nest in each of the images, wherein the image recognition result includes the first bird's nest boundary;
[0011] Based on the boundaries of each of the first bird's nests and the images from the multiple perspectives, it is determined whether the shape of the area where the bird's nest is located is an open area.
[0012] Optionally, the multiple perspectives are different from each other, and determining whether the shape of the area where the bird's nest is located is an open area based on the boundaries of each first bird's nest and the images from the multiple perspectives includes:
[0013] For each of the multiple perspectives, selecting a first bird's nest boundary corresponding to the perspective from the first bird's nest boundaries;
[0014] Determining a visible surface bird's nest boundary from the first bird's nest boundaries corresponding to the multiple perspectives based on the first bird's nest boundaries corresponding to the multiple perspectives, the images of the multiple perspectives, and preset bird's nest morphological characteristics;
[0015] When the number of the visible bird's nest boundaries is greater than a preset number threshold, it is determined that the shape of the area where the bird's nest is located is an open area.
[0016] Optionally, the method further includes:
[0017] When the area where the bird's nest is located is an open area, a multispectral image and an ultrasonic image corresponding to the high-voltage switch mechanism of the substation are obtained; based on the multispectral image and the ultrasonic image, the nesting material information of the bird's nest is determined; based on the nesting material information and the visible light image, a safe removal device is controlled to remove the bird's nest.
[0018] Optionally, determining the nesting material information of the bird's nest based on the multispectral image and the ultrasonic image includes:
[0019] extracting infrared features of the bird's nest from the multispectral image, and extracting density features of the bird's nest from the ultrasonic image, wherein the infrared features are suitable for indicating reflection information of a near-infrared band and / or reflection information of a short-wave infrared band, and the density features are suitable for indicating material density;
[0020] Performing weighted fusion on the infrared features and the density features to obtain a multimodal feature vector;
[0021] Based on the multimodal feature vector, the bird's nest is classified according to the degree of material hazard, and nesting material information of the bird's nest is generated according to the classification result, wherein the classification result includes whether the nest contains hazardous materials or non-hazardous materials.
[0022] Optionally, classifying the material hazard level of the bird's nest based on the multimodal feature vector includes:
[0023] The multimodal feature vector is input into a pre-trained database model to obtain the classification result output by the database model.
[0024] In the second aspect, an embodiment of the present application provides a device for removing bird nests on a high-voltage switch mechanism of a substation, the device comprising a controller and a working part communicatively connected to the controller, wherein the controller is configured to execute any of the methods described above, and the safe removal device is the working part.
[0025] Optionally, the working part includes a supporting mechanism and a puncture mechanism, the puncture mechanism is arranged at one end of the supporting mechanism, the puncture mechanism has an open state and a closed state, and a retractable puncture piece is provided at one end of the puncture mechanism, the puncture piece is used to puncture the bird's nest, and the puncture piece is retracted and extended as the puncture mechanism switches between the closed state and the open state.
[0026] Optionally, the puncture mechanism includes a puncture mechanism body and an umbrella-net structure, the puncture mechanism body is fixed to one end of the support mechanism, and the umbrella-net structure and the puncture member are both provided at the same end of the puncture mechanism body;
[0027] When the puncture mechanism is in the closed state, the umbrella-net structure is closed to form a closed space, and the puncture member is accommodated in the closed space;
[0028] When the puncture mechanism is in the open state, the umbrella-net structure is opened to expose the puncture member;
[0029] During the switching process of the puncture mechanism from the closed state to the open state, the puncture member punctures in a direction away from the puncture mechanism body.
[0030] Optionally, the end of the piercing member facing away from the puncture mechanism is configured as a spike, and the side surface of the piercing member is provided with a barb.
[0031] In summary, the embodiments of the present application have at least the following beneficial effects:
[0032] According to an embodiment of the present application, a visible light image corresponding to the high-voltage knife switch mechanism of the substation is obtained; image recognition is performed on the visible light image, and the shape of the area where the bird's nest is located is determined based on the image recognition result, wherein the shape of the area where the bird's nest is located includes an open area or a semi-enclosed area. When the visible light image includes a hole image, the hole image contains a hole and a portion of the bird's nest observed through the hole. The image recognition result includes a second bird's nest boundary of the portion of the nest detected in the hole image and a hole boundary of the hole. If the overlap rate is greater than a preset overlap rate threshold, it is determined that the shape of the area where the bird's nest is located is a semi-enclosed area, and the overlap rate is determined based on the second bird's nest boundary and the hole boundary. When the shape of the area where the bird's nest is located is a semi-enclosed area, the safety removal device is controlled to remove the bird's nest based on the visible light image, so that the bird's nest on the high-voltage knife switch mechanism of the substation can be accurately removed, especially the bird's nest in the semi-enclosed area, thereby reducing the safety risk during the bird's nest removal process. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] Figure 1 1 is a flow chart of a method for removing a bird's nest on a high-voltage switch mechanism of a substation provided by an embodiment of the present application;
[0034] Figure 2 1. It is a structural schematic diagram of a device for removing bird's nests on a high-voltage switch mechanism of a substation provided by an embodiment of the present application;
[0035] Figure 3 1. It is a top view schematic diagram of a device for removing a bird's nest on a high-voltage switch mechanism of a substation provided by an embodiment of the present application;
[0036] Figure 4 1. It is a structural schematic diagram of a device for removing bird's nests on a high-voltage switch mechanism of a substation provided by an embodiment of the present application;
[0037] Figure 5 It is a structural diagram of the computer device provided in an embodiment of the present application.
[0038] Reference numerals:
[0039] 11- puncture member; 12- puncture mechanism body; 13- umbrella net structure;
[0040] 2-support mechanism; 3-box body; 4-insulating rod;
[0041] 501-processor; 502-memory. DETAILED DESCRIPTION
[0042] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.
[0043] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, features defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of such features. In the description of this application, unless otherwise specified, "multiple" means two or more. In the description of this application, the term "including" and its variations are open inclusions, i.e., "including but not limited to". The term "based on" means "at least partially based on". The term "according to" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments".
[0044] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.
[0045] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in this application have the same meanings as those commonly understood by those skilled in the art. The terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit this application. Those of ordinary skill in the art will understand the specific meanings of the above terms in this application in specific circumstances.
[0046] First, see Figure 1 , shows a flow chart of a method for removing a bird's nest on a high-voltage switch mechanism of a substation provided by an embodiment of the present application, the method includes S101-S103, as follows.
[0047] S101, obtaining a visible light image corresponding to the high-voltage switch mechanism of the substation.
[0048] In some examples, the working part of the cleaning device described in the present application may be provided with a camera, which may include a visible light camera, and the above-mentioned visible light image may be obtained by capturing the visible light camera.
[0049] S102, performing image recognition on the visible light image, and judging the shape of the area where the bird's nest is located based on the image recognition result, wherein the shape of the area where the bird's nest is located includes an open area or a semi-enclosed area. In the case where the visible light image includes a hole image, the hole image contains a hole and a portion of the bird's nest observed through the hole. The image recognition result includes a second bird's nest boundary of the portion of the nest detected in the hole image and a hole boundary of the hole. If an overlap rate is greater than a preset overlap rate threshold, it is determined that the shape of the area where the bird's nest is located is a semi-enclosed area, and the overlap rate is determined based on the second bird's nest boundary and the hole boundary.
[0050] In some examples, a pre-trained regional morphology recognition model can be used to perform image recognition on visible light images to determine the morphology of the area where the bird's nest is located, wherein the regional morphology recognition model can be a model that has been trained to have the predictive ability to use visible light images as model input and the morphology of the area where the bird's nest is located as model output. During specific training, sample visible light images of bird's nests located on the high-voltage switch mechanism of the substation can be used as sample data (the sample data also carries the expected corresponding morphology label, which represents the expected morphology of the area where the corresponding bird's nest is located), and a general training algorithm (such as the gradient descent method) is used to train the model so that the model after training can have the above-mentioned capabilities.
[0051] It is understood that the open area represents a bird's nest located on a fully exposed gate mechanism, while the semi-enclosed area represents a bird's nest hidden in a box-like structure, with only part of the nest visible through a hole (such as the tip of a branch or a wire protruding).
[0052] In some examples, the preset overlap rate threshold is 30%.
[0053] In some examples, due to the visibility characteristic of bird nests located in semi-enclosed areas, the nests are partially exposed. In this case, the nests are usually hidden in a box-like structure (such as the gap in the body of the high-voltage knife mechanism, the gap in the top of the high-voltage knife mechanism porcelain bottle, etc.), and only part of the nest body (such as the tip of a protruding branch, metal wire, etc.) can be observed through the hole. The main body of the nest is invisible and has a scattered distribution feature, which may only show a single side or local accumulation. Therefore, the nest area visible through the hole appears as irregular fragments with blurred edges. Therefore, whether the shape of the area where the nest is located is a semi-enclosed area can be determined by judging whether the above-mentioned overlap rate is greater than a preset overlap rate threshold. The overlap rate can refer to the ratio of the length of the boundary line overlapping between the second nest boundary and the hole boundary to the length of the second nest boundary or the length of the hole boundary. The preset overlap rate threshold can be adjusted accordingly.
[0054] In some examples, the overlap ratio may also refer to the ratio of the overlapping area between the areas enclosed by the second bird's nest boundary and the hole boundary to the area of the area enclosed by the second bird's nest boundary or the area of the area enclosed by the hole boundary.
[0055] In some examples, since the depth direction of the bird's nest only shows one side, the hole size can also be combined to confirm the structure of the semi-enclosed area.
[0056] S103 : When the area where the bird's nest is located is a semi-enclosed area, control a safety clearing device to clear the bird's nest based on the visible light image.
[0057] In some examples, the above-mentioned safety clearing device includes a support mechanism and a puncture mechanism, the puncture mechanism is arranged at one end of the support mechanism, the puncture mechanism has an open state and a closed state, one end of the puncture mechanism is provided with a retractable and movable puncture piece, the puncture piece is used to puncture the bird's nest, the puncture mechanism includes a puncture mechanism body and an umbrella net structure, the puncture mechanism body is fixed to one end of the support mechanism, the umbrella net structure and the puncture piece are both arranged at the same end of the puncture mechanism body; when the puncture mechanism is in the closed state, the umbrella net structure is closed to form a closed space, and the puncture piece is accommodated in the closed space; when the puncture mechanism is in the open state, the umbrella net structure is opened to expose the puncture piece; during the switching process of the puncture mechanism from the closed state to the open state, the puncture piece punctures in a direction away from the puncture mechanism body.
[0058] Continuing with the above example, controlling the safety clearing device to clear the bird's nest based on the visible light image may include: controlling the puncture mechanism to move to a position corresponding to the bird's nest based on the visible light image; controlling the puncture mechanism to puncture toward the bird's nest at the position, and switching from the closed state to the open state during the puncture process, so that the puncture member can pierce the bird's nest and the umbrella net structure is opened; after the puncture is completed, controlling the puncture mechanism to retract, and switching from the open state to the closed state during the retraction process, so that the puncture member contracts and the umbrella net structure is closed, thereby placing the bird's nest in the above-mentioned closed space, so as to complete the clearing of the bird's nest after the puncture mechanism is retracted.
[0059] In an optional embodiment, the visible light image includes images from multiple perspectives, and performing image recognition on the visible light image and determining the shape of the area where the bird's nest is located based on the image recognition result includes:
[0060] performing edge detection on each of the images from the multiple perspectives to obtain a first bird's nest boundary of the bird's nest in each of the images, wherein the image recognition result includes the first bird's nest boundary;
[0061] Based on the boundaries of each of the first bird's nests and the images from the multiple perspectives, it is determined whether the shape of the area where the bird's nest is located is an open area.
[0062] In some examples, the above edge detection can be implemented by using the Canny algorithm.
[0063] In some examples, due to the visibility characteristic of the open area, the bird's nest is exposed from multiple perspectives. At this time, the bird's nest is located on a completely exposed gate mechanism. Except for the bottom and the contact surface with the puncture mechanism, all other sides are visible, and the bird's nest is complete in shape, with a regular stacking shape (such as a spherical or bowl-shaped shape), a clear outline, and completely visible surface textures (such as crossed branches and entangled wires). Therefore, the three-dimensional structure of the bird's nest can be reconstructed based on the first bird's nest boundaries and the images of the multiple perspectives, and the ratio between the surface area and volume of the bird's nest is calculated accordingly, so as to determine whether the shape of the area where the bird's nest is located is an open area based on the ratio (for example, comparing the ratio with a preset ratio threshold).
[0064] In an optional embodiment, the multiple perspectives are different from each other, and determining whether the shape of the area where the bird's nest is located is an open area based on the boundaries of each first bird's nest and the images from the multiple perspectives includes:
[0065] For each of the multiple perspectives, selecting a first bird's nest boundary corresponding to the perspective from the first bird's nest boundaries;
[0066] Determining a visible surface bird's nest boundary from the first bird's nest boundaries corresponding to the multiple perspectives based on the first bird's nest boundaries corresponding to the multiple perspectives, the images of the multiple perspectives, and preset bird's nest morphological characteristics;
[0067] When the number of the visible bird's nest boundaries is greater than a preset number threshold, it is determined that the shape of the area where the bird's nest is located is an open area.
[0068] In some examples, due to the visibility characteristic of a bird's nest located in an open area, the nest is exposed from multiple perspectives. In this case, the nest is located on a completely exposed gate mechanism, and except for the bottom and the contact surface with the puncture mechanism, all other sides are visible. The nest is also complete in shape, with a regularly stacked shape (such as a sphere or bowl), a clear outline, and fully visible surface textures (such as intersecting branches and entangled wires). Therefore, in this case, in images from different multiple perspectives, there should be multiple images that capture the complete outline of the nest. The corresponding first nest boundaries can be used to compare with the preset nest morphological characteristics. It is understandable that in this case, only one first nest boundary needs to be selected from each perspective to determine whether it meets the nest morphological characteristics from that perspective. In this way, the number of visible nest boundaries obtained is equal to the number of perspectives from which the complete nest outline can be observed.
[0069] In some examples, the bird's nest morphological characteristics may include contour characteristics and surface texture characteristics. Based on the first bird's nest boundaries corresponding to each of the multiple perspectives, the images of the multiple perspectives, and the preset bird's nest morphological characteristics, the visible surface bird's nest boundary is determined from the first bird's nest boundaries corresponding to each of the multiple perspectives. It may include: based on the first bird's nest boundaries corresponding to each of the multiple perspectives, a third bird's nest boundary that meets the contour characteristics is determined from the first bird's nest boundaries corresponding to each of the multiple perspectives, wherein the contour characteristics are used to indicate that the bird's nest boundary is a regular shape, and the regular shape includes a circle, an ellipse, a semicircle and / or a semi-ellipse; based on the images of the multiple perspectives, a visible surface bird's nest boundary that meets the surface texture characteristics is determined from each of the third bird's nest boundaries, wherein the surface texture characteristics are used to indicate that there are crossed branches, entangled wires, etc. on the bird's nest surface, and the bird's nest surface is detected from the images of the multiple perspectives based on the third bird's nest boundary.
[0070] In some examples, the preset quantity threshold may be 3.
[0071] In an optional embodiment, the method may further include:
[0072] When the area where the bird's nest is located is an open area, a multispectral image and an ultrasonic image corresponding to the high-voltage switch mechanism of the substation are obtained; based on the multispectral image and the ultrasonic image, the nesting material information of the bird's nest is determined; based on the nesting material information and the visible light image, a safe removal device is controlled to remove the bird's nest.
[0073] In some examples, the nesting material information can be determined based on the multispectral image and the ultrasonic image using a pre-trained nesting material recognition model, wherein the nesting material recognition model can be a model that has been trained to have the predictive capability of using the multispectral image and the ultrasonic image as model input and the nesting material information as model output. During specific training, sample multispectral images and sample ultrasonic images can be used as sample data (the sample data also carries the expected corresponding material label, which represents the corresponding expected material information), and a general training algorithm (such as the gradient descent method) can be used to train the model, so that the model after training can have the above-mentioned capabilities.
[0074] In some examples, a sensor may be provided on the working part of the cleaning device described in the present application, and the sensor may include a multispectral sensor and / or an ultrasonic sensor. The multispectral image may be generated by detection via the multispectral sensor, and the ultrasonic image may be generated by detection via the ultrasonic sensor.
[0075] In some examples, controlling the safety clearing device to clear the bird's nest based on the nesting material information and the visible light image may include: when the nesting material information indicates that the bird's nest contains hazardous materials, controlling the puncture mechanism to move to a position corresponding to the bird's nest based on the visible light image; controlling the puncture mechanism to puncture toward the bird's nest at the position, and switching from the closed state to the open state during the puncture process, so that the puncture member can penetrate into the bird's nest and the umbrella net structure is opened; after the puncture is completed, controlling the puncture mechanism to retract, and switching from the open state to the closed state during the retraction process, so that the puncture member contracts and the umbrella net structure is closed, thereby placing the bird's nest in the above-mentioned closed space, so as to complete the clearing of the bird's nest after the puncture mechanism is retracted. In the case where the nesting material information indicates that the bird's nest is made of non-hazardous materials, a prompt message can be output to the user. The prompt message can be used to prompt the user to remove the bird's nest by manual hooking. This is because the bird's nest is located in an open area and does not contain hazardous materials. Manual hooking does not bring high risks. Of course, the puncture mechanism can also be directly controlled in the same way as "the nesting material information indicates that the bird's nest contains hazardous materials", which will not be repeated here.
[0076] In some examples, after controlling the safety clearing device to clear the bird's nest, a real-time image corresponding to the high-voltage switch mechanism of the substation can be re-acquired to determine whether the bird's nest has been completely cleared based on the real-time image.
[0077] In an optional embodiment, determining the nesting material information of the bird's nest based on the multispectral image and the ultrasonic image includes:
[0078] extracting infrared features of the bird's nest from the multispectral image, and extracting density features of the bird's nest from the ultrasonic image, wherein the infrared features are suitable for indicating reflection information of a near-infrared band and / or reflection information of a short-wave infrared band, and the density features are suitable for indicating material density;
[0079] Performing weighted fusion on the infrared features and the density features to obtain a multimodal feature vector;
[0080] Based on the multimodal feature vector, the bird's nest is classified according to the degree of material hazard, and nesting material information of the bird's nest is generated according to the classification result, wherein the classification result includes whether the nest contains hazardous materials or non-hazardous materials.
[0081] In some examples, the aforementioned hazardous materials may refer to the material of the bird's nest containing hazardous materials such as metal wire.
[0082] In some examples, the reflection information may include a reflection curve.
[0083] In some examples, since metal density is usually ≥7.8 g / cm³ and tree branches are ≈0.6 g / cm³, metal density is greater than tree branch density. Therefore, the density feature can be used to determine whether the material of the bird's nest contains dangerous materials such as metal wire.
[0084] In some examples, the above weighted fusion formula may include:
[0085]
[0086] in, is the i-th modal feature, is the weight of the i-th modal feature, Represents the output after the nonlinear transformation of the i-th modal feature by the multi-layer perceptron, is the multimodal feature vector, is the number of modal features, is the activation function used to convert the output into a probability distribution.
[0087] in, , Represents infrared features (or multispectral image features), Represents density features (or ultrasonic image features).
[0088] In an optional embodiment, classifying the material hazard level of the bird's nest based on the multimodal feature vector includes:
[0089] The multimodal feature vector is input into a pre-trained database model to obtain the classification result output by the database model.
[0090] In some examples, the database model can be obtained by training a model such as a neural network using a material-image correspondence library, where the material-image correspondence library includes different materials and corresponding different images.
[0091] In the second aspect, an embodiment of the present application provides a device for removing bird nests on a high-voltage switch mechanism of a substation, the device comprising a controller and a working part communicatively connected to the controller, wherein the controller is configured to execute any of the methods described above, and the safe removal device is the working part.
[0092] In some examples, the controller may include an MCU (Microcontroller Unit) microcontroller. The model of the MCU microcontroller may be the STM32F103 series, which has a low price. Furthermore, this embodiment may use an STM32F103C8T6 chip.
[0093] Please also refer to Figure 2-Figure 4 .
[0094] In an optional embodiment, the working part includes a support mechanism 2 and a puncture mechanism, the puncture mechanism is arranged at one end of the support mechanism 2, the puncture mechanism has an open state and a closed state, and a retractable puncture member 11 is provided at one end of the puncture mechanism, the puncture member 11 is used to puncture the bird's nest, and the puncture member 11 is retracted and extended as the puncture mechanism switches between the closed state and the open state.
[0095] In some examples, the support mechanism 2 can be rod-shaped. The support mechanism 2 can be an insulating rod with a length greater than 3 meters and / or an adjustable length that can withstand a high voltage of 500 kV. The support mechanism 2 can be provided with a visualization module (e.g., a display screen). The visualization module can be used to display any image described in any embodiment of the present application for real-time viewing by an operator on the ground, and can also be used to provide a function for controlling the puncture mechanism. A communication connection can be established between the controller, the visualization module, and the puncture mechanism via a communication transceiver module. The communication transceiver module can include a 2.4G wireless transceiver module installed on the visualization module and the puncture mechanism, respectively. Exemplarily, the 2.4G wireless transceiver module is a 2.4G communication module of model JF24D-TX / RX.
[0096] For some examples, see Figure 2 and Figure 4 The above-mentioned safe clearing device also includes an insulating rod 4 (only a part of the insulating rod 4 is shown in the figure), and the end of the support mechanism 2 away from the puncture mechanism is used for detachable connection with the insulating rod 4.
[0097] In some examples, after the controller determines the clearing strategy by executing any of the methods described above, the clearing strategy can be displayed in the above-mentioned visualization module, and after receiving the policy confirmation instruction input by the user through the above-mentioned visualization module, the safety clearing device can be controlled to clear the bird's nest.
[0098] In some examples, the cleaning device may further include a box body 3, which may be mounted on the outside of the support mechanism 2, and an inner wall of the box body 3 and an outer side surface of the support mechanism 2 are spaced apart, thereby defining a storage space between the inner wall of the box body 3 and the outer side surface of the support mechanism 2, and the storage space may be used to accommodate a controller, the motor described below, and / or the power supply module described below, etc.
[0099] In addition, see Figure 4 The box body 3 can also be fixed on one side of the support mechanism 2. Similarly, there is a distance between the inner wall of the box body 3 and the side of the support mechanism 2, thereby defining a storage space between the inner wall of the box body 3 and the side of the support mechanism 2. The storage space can be used to accommodate a controller, the motor described below, and / or the power module described below, etc.
[0100] It is understandable that one end of the support mechanism 2 away from the puncture mechanism body 12 will be exposed from the box body 3 to facilitate the user to hold it.
[0101] In an optional embodiment, the puncture mechanism includes a puncture mechanism body 12 and an umbrella-net structure 13, wherein the puncture mechanism body 12 is fixed to one end of the support mechanism 2, and the umbrella-net structure 13 and the puncture member 11 are both provided at the same end of the puncture mechanism body 12;
[0102] When the puncture mechanism is in the closed state, the umbrella-net structure 13 is closed to form a closed space, and the puncture member 11 is accommodated in the closed space;
[0103] When the puncture mechanism is in the open state, the umbrella-net structure 13 is opened to expose the puncture member 11;
[0104] During the switching process of the puncture mechanism from the closed state to the open state, the puncture member 11 punctures in a direction away from the puncture mechanism body 12 .
[0105] It is understandable that Figure 2-Figure 4 The umbrella net structure 13 in the figure actually only shows the umbrella frames, and the umbrella frames are connected by umbrella nets (not shown in the figure).
[0106] In some examples, the umbrella net structure 13 may include a spring energy storage module and multiple ribs. Initially, the spring energy storage module is compressed by a locking member, storing elastic potential energy to power the umbrella net's deployment. When the ribs are folded, they are closed. When the lock is released, the spring preload is instantly released, pushing the central rail axially, causing the ribs to deploy.
[0107] In some examples, when controlling the safety clearing device to clear the bird's nest, the puncture mechanism is controlled to switch from the closed state to the open state, so that the puncture member 11 is exposed and extended and penetrates into the bird's nest, and then the puncture mechanism is controlled to switch from the open state to the closed state, so that the puncture member 11 is retracted, the bird's nest is taken out and at the same time, the closed space formed by closing the umbrella net structure 13 is used to wrap the bird's nest to prevent the bird's nest from escaping.
[0108] In some examples, the puncture mechanism body 12 may further include a motor, and the output shaft of the motor may be connected to the umbrella net structure 13 and the puncture member 11 in sequence through a reducer, a screw rod, and a net-tensioning mechanism, so that the output shaft of the motor may be connected to the umbrella net structure 13 and the puncture member 11 in sequence through a reducer, a screw rod, and a net-tensioning mechanism to provide the umbrella net structure 13 with power for switching between a closed state and an open state, and to provide the puncture member 11 with power for telescopic movement.
[0109] In some examples, the motor's output shaft can be connected to a reducer (such as a planetary gear reducer with a 30:1 reduction ratio) via a coupling, reducing the speed to 100 rpm and increasing the torque to 36 N·m. The reducer's output drives a lead screw (a ball screw pair), converting the rotational motion into linear motion of the nut.
[0110] When the piercing element 11 penetrates the bird's nest, the motor rotates forward, causing the screw shaft to rotate clockwise. The nut moves forward along the guide rail (at a speed of 5-20 mm / s), pushing the piercing element 11 into the nest. When the nut reaches the preset position (penetration depth of 200 mm, adjustable), a mechanical stop block or Hall effect sensor is triggered. This limit signal is fed back to the controller, causing the motor to stop immediately to prevent excessive penetration and damage to the equipment's insulation.
[0111] During the umbrella net expansion phase, as the piercing member 11 begins penetration, the movement of the nut triggers the unlocking catch (mechanical linkage), releasing the locking mechanism. Once unlocked, the compression spring expands freely, pushing the umbrella-shaped frame radially to expand to a diameter of 200-300mm. After the spring reaches its maximum travel, a limit pin secures the expansion angle.
[0112] During the net closing phase, the motor rotates in reverse, and the nut drives the piercing member 11 to retract linearly. During the retraction process, the net frame compresses the spring to its initial state through the connecting rod mechanism. The locking mechanism re-secures the spring to keep the net closed.
[0113] In some examples, the cleaning device may further include a power module. The motor may be a DC motor driven by a DC motor, and the magnitude and direction of the current may control the speed and direction of the motor's rotor. The power module may use a DC power supply to power the DC motor and may also be used to power the controller and visualization module. The power module may include a lithium battery or a lead-acid battery. Preferably, the power module is a lithium battery. Exemplarily, the selected lithium battery model is YSN240-2600, which has a higher energy density for the same weight or volume and can store more energy.
[0114] In an optional embodiment, the end of the piercing member 11 facing away from the puncture mechanism is configured as a spike, and the side surface of the piercing member 11 is provided with a barb.
[0115] In some examples, the piercing member 11 is specifically a piercing rod, and the number of barbs is multiple, each of which is spaced apart and arranged on the side of the piercing member 11 / piercing rod around the main axis. The barbs face the piercing mechanism. The barbs are specifically barb blades, whose tips are designed with curved cutting edges to reduce piercing resistance. When the barb blades are deployed, they form an anchoring structure. The connection between the barb blade and the piercing rod is provided with an axis. The barb blade rotates around the axis from 0° (stowed state) to 90° (deployed state). When rotated to 0°, the barb blade rotates around the axis until it is parallel to the piercing rod, fully embedded in the slot, and the surface is flush with the rod body, reducing piercing resistance. The barb blade rotates around the axis to 90° (perpendicular to the piercing rod), forming an anchoring structure.
[0116] The cleaning device described in the relevant embodiments of the present application may have at least one of the following advantages.
[0117] 1. The existing bird nest removal device cannot remove the bird nest at the semi-enclosed gate mechanism. The present application designs a barbed puncture mechanism at the top of the device, which can effectively remove the bird nest in the hidden position of the semi-enclosed gate mechanism.
[0118] 2. Existing bird nest removal devices have the risk of insufficient safety distance, endangering the personal safety of operators. This application uses wireless communication technology to effectively protect the personal safety of operators.
[0119] 3. The existing bird nest removal device takes too long to remove bird nests. The bird nest removal device of this application can remove bird nests in open positions, as well as bird nests in hidden positions of semi-enclosed knife mechanisms, without the need for power outages. All bird nest scenarios can be handled in an energized environment. The device realizes convenient removal and effectively shortens the bird nest removal time to 10 minutes.
[0120] 4. The existing bird nest removal device cannot monitor the bird nest removal process in real time. This application is based on high-definition imaging technology. A high-definition camera is installed on the top of the device and a display screen is installed at the bottom of the device. The operator can realize real-time viewing of the bird nest inside the equipment on the ground, accurately judge the status of the nesting material, and assist in optimizing the puncture and recovery operations.
[0121] In a third aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for removing a bird's nest on a high-voltage switch mechanism of a substation as described above.
[0122] In a fourth aspect, an embodiment of the present application provides a computer program product, comprising computer instructions, which, when executed by a processor, implement the steps of the method for removing a bird's nest on a high-voltage switch mechanism of a substation as described in any one of the above items.
[0123] In a fifth aspect, an embodiment of the present application provides a computer device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the steps of the method for removing the bird's nest on the high-voltage switch mechanism of the substation as described in any one of the above items are implemented.
[0124] See also Figure 5 The computer device of this embodiment includes: a processor 501, a memory 502, and a computer program stored in the memory 502 and executable on the processor 501, such as a program for removing bird nests from a high-voltage switch mechanism of a substation. When the processor 501 executes the computer program, the steps of the above-mentioned methods for removing bird nests from a high-voltage switch mechanism of a substation are implemented, such as Figure 1 Steps S101-S103 are shown.
[0125] For example, the computer program may be divided into one or more modules / units, which are stored in the memory 502 and executed by the processor 501 to implement the present application. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in the computer device.
[0126] The computer device may be a desktop computer, laptop, PDA, cloud server, or other computing device. The computer device may include, but is not limited to, a processor 501 and a memory 502. Those skilled in the art will appreciate that the schematic diagram is merely an example of a computer device and does not limit the computer device. The computer device may include more or fewer components than shown, or a combination of certain components, or different components. For example, the computer device may also include input and output devices, network access devices, buses, and the like.
[0127] The processor 501 may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor 501 may be any conventional processor. The processor 501 is the control center of the computer device, connecting various parts of the entire computer device using various interfaces and lines.
[0128] The memory 502 can be used to store the computer programs and / or modules. The processor 501 implements the various functions of the computer device by running or executing the computer programs and / or modules stored in the memory 502 and accessing the data stored in the memory 502. The memory 502 may mainly include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as a sound playback function or an image playback function); the data storage area may store data generated based on the use of the mobile phone (such as audio data, a phone book, etc.). In addition, the memory 502 may include high-speed random access memory and non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.
[0129] If the module / unit integrated into the computer device is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application can implement all or part of the process in the above-mentioned embodiment method by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor 501, it can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium.
[0130] In summary, the embodiments of the present application have at least the following beneficial effects:
[0131] According to an embodiment of the present application, a visible light image corresponding to the high-voltage knife switch mechanism of the substation is obtained; image recognition is performed on the visible light image, and the shape of the area where the bird's nest is located is determined based on the image recognition result, wherein the shape of the area where the bird's nest is located includes an open area or a semi-enclosed area. When the visible light image includes a hole image, the hole image contains a hole and a portion of the bird's nest observed through the hole. The image recognition result includes a second bird's nest boundary of the portion of the nest detected in the hole image and a hole boundary of the hole. If the overlap rate is greater than a preset overlap rate threshold, it is determined that the shape of the area where the bird's nest is located is a semi-enclosed area, and the overlap rate is determined based on the second bird's nest boundary and the hole boundary. When the shape of the area where the bird's nest is located is a semi-enclosed area, the safety removal device is controlled to remove the bird's nest based on the visible light image, so that the bird's nest on the high-voltage knife switch mechanism of the substation can be accurately removed, especially the bird's nest in the semi-enclosed area, thereby reducing the safety risk during the bird's nest removal process.
[0132] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present application can be implemented by means of software plus the necessary hardware platform, and of course, it can also be implemented entirely through hardware. Based on this understanding, all or part of the contribution of the technical solution of the present application to the background technology can be embodied in the form of a software product. The computer software product can be stored in a storage medium, such as ROM (Read-Only Memory) / RAM (Random Access Memory), a disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application or certain parts of the embodiments.
[0133] The above is a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications are also considered to be within the scope of protection of the present application.
Claims
1. A method for removing bird nests on a high-voltage switch mechanism of a substation, characterized in that: include: Acquire a visible light image corresponding to the high-voltage switch mechanism of the substation; performing image recognition on the visible light image, and determining, based on the image recognition result, a morphology of the area where the bird's nest is located, wherein the morphology of the area where the bird's nest is located includes an open area or a semi-enclosed area. If the visible light image includes a hole image, the hole image includes a hole and a portion of the bird's nest observed through the hole. The image recognition result includes a second nest boundary of the portion of the nest detected in the hole image and a hole boundary of the hole. If an overlap rate is greater than a preset overlap rate threshold, determining that the morphology of the area where the bird's nest is located is a semi-enclosed area, the overlap rate being determined based on the second nest boundary and the hole boundary. When the area where the bird's nest is located is a semi-enclosed area, controlling a safety clearing device to clear the bird's nest based on the visible light image; When the area where the bird's nest is located is an open area, a multispectral image and an ultrasonic image corresponding to the high-voltage switch mechanism of the substation are obtained; based on the multispectral image and the ultrasonic image, the nesting material information of the bird's nest is determined; based on the nesting material information and the visible light image, a safe removal device is controlled to remove the bird's nest.
2. The method according to claim 1, characterized in that The visible light image includes images from multiple perspectives, and performing image recognition on the visible light image and determining the shape of the area where the bird's nest is located based on the image recognition result includes: performing edge detection on each of the images from the multiple perspectives to obtain a first bird's nest boundary of the bird's nest in each of the images, wherein the image recognition result includes the first bird's nest boundary; Based on the boundaries of each of the first bird's nests and the images from the multiple perspectives, it is determined whether the shape of the area where the bird's nest is located is an open area.
3. The method according to claim 2, characterized in that The multiple perspectives are different from each other, and determining whether the shape of the area where the bird's nest is located is an open area based on the boundaries of each first bird's nest and the images from the multiple perspectives includes: For each of the multiple perspectives, selecting a first bird's nest boundary corresponding to the perspective from the first bird's nest boundaries; Determining a visible surface bird's nest boundary from the first bird's nest boundaries corresponding to the multiple perspectives based on the first bird's nest boundaries corresponding to the multiple perspectives, the images of the multiple perspectives, and preset bird's nest morphological characteristics; When the number of the visible bird's nest boundaries is greater than a preset number threshold, it is determined that the shape of the area where the bird's nest is located is an open area.
4. The method according to any one of claims 1 to 3, characterized in that The determining of nesting material information of the bird's nest based on the multispectral image and the ultrasonic image includes: extracting infrared features of the bird's nest from the multispectral image, and extracting density features of the bird's nest from the ultrasonic image, wherein the infrared features are suitable for indicating reflection information of a near-infrared band and / or reflection information of a short-wave infrared band, and the density features are suitable for indicating material density; Performing weighted fusion on the infrared features and the density features to obtain a multimodal feature vector; Based on the multimodal feature vector, the bird's nest is classified according to the degree of material hazard, and nesting material information of the bird's nest is generated according to the classification result, wherein the classification result includes whether the nest contains hazardous materials or non-hazardous materials.
5. The method according to claim 4, characterized in that The step of classifying the material hazard level of the bird's nest based on the multimodal feature vector includes: The multimodal feature vector is input into a pre-trained database model to obtain the classification result output by the database model.
6. A device for removing bird nests from high voltage switch mechanism of a substation, characterized in that: The clearing device includes a controller and a working part communicatively connected to the controller, wherein the controller is configured to execute the method according to any one of claims 1 to 5, and the safe clearing device is the working part.
7. The cleaning device according to claim 6, characterized in that The working part includes a supporting mechanism and a puncture mechanism. The puncture mechanism is arranged at one end of the supporting mechanism. The puncture mechanism has an open state and a closed state. A retractable puncture piece is provided at one end of the puncture mechanism. The puncture piece is used to puncture the bird's nest. The puncture piece is retractable as the puncture mechanism switches between the closed state and the open state.
8. The cleaning device according to claim 7, characterized in that The puncture mechanism includes a puncture mechanism body and an umbrella-net structure, wherein the puncture mechanism body is fixed to one end of the support mechanism, and the umbrella-net structure and the puncture member are both arranged at the same end of the puncture mechanism body; When the puncture mechanism is in the closed state, the umbrella-net structure is closed to form a closed space, and the puncture member is accommodated in the closed space; When the puncture mechanism is in the open state, the umbrella-net structure is opened to expose the puncture member; During the switching process of the puncture mechanism from the closed state to the open state, the puncture member punctures in a direction away from the puncture mechanism body.
9. The cleaning device according to claim 7, characterized in that The end of the piercing member facing away from the piercing mechanism is configured as a spike, and a side surface of the piercing member is provided with a barb.
Citation Information
Patent Citations
Intelligent substation inspection robot with bird repelling function
CN111345277A
Power transmission line nest hazard grade identification method and device, and computer equipment
CN119445455A