Line component identification and alarm method and system based on unmanned detector
Through unmanned detector identification and deep learning network analysis, the problem of low line troubleshooting efficiency and accuracy in the power industry is solved, and the rapid and accurate identification of line components and temperature detection are achieved, and the troubleshooting efficiency and accuracy are improved.
Patent Information
- Application Number
- CN202211412490.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-11-11
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2042-11-11
AI Technical Summary
The fault detection efficiency and accuracy of outdoor power transmission lines in the existing power industry are low, and manual or aircraft identification methods have problems such as low efficiency and low recognition accuracy.
The line component identification and alarm method based on the unmanned detector is adopted, and the main component of the line is identified through the unmanned detector, the target image data is collected and the deep learning network is used to detect the temperature of the line sub-components, and whether it exceeds the preset temperature threshold. If it exceeds the alarm information, the user will be reminded to take corresponding processing.
It improves the efficiency and accuracy of line troubleshooting, can quickly monitor the status of line components in real time, quickly inform users of fault location and type, and promotes the efficiency and accuracy of troubleshooting.
Smart Images

Figure CN115762083B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of electric power detection, and in particular to a line component identification and alarm method and system based on unmanned detectors. Background Art
[0002] In the current power industry, the existing troubleshooting method for outdoor power transmission lines generally uses manual detection or aircraft identification detection to check the line components of each section of the transmission line that needs to be detected on site section by section. However, the troubleshooting ability of this manual or aircraft identification troubleshooting method is not high, and there are problems such as low troubleshooting efficiency and low recognition accuracy during the troubleshooting process. A line component identification and alarm method and system based on unmanned detectors are currently provided to accurately troubleshoot the transmission line fault detection process to solve the problem of low efficiency and accuracy of transmission line fault detection in the current power industry. Summary of the invention
[0003] The technical problem to be solved by the present invention is to provide a line component identification and alarm method and system based on unmanned detectors, which can effectively improve the efficiency and accuracy of fault detection of transmission lines in power operations.
[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a line component identification and alarm method based on an unmanned detector, the method comprising:
[0005] Identifying the main line components of the line section to be inspected by an unmanned detector, and collecting target image data of the main line components;
[0006] Receiving the target image data sent by the unmanned detector, and identifying the target image data through a deep learning network to obtain an identification result, wherein the identification result includes target line subcomponents of a plurality of the line main components;
[0007] Detecting the temperature values of all circuit subcomponents by the unmanned detector, receiving the temperature values of all circuit subcomponents sent by the unmanned detector, and determining whether the temperature value of each circuit subcomponent is greater than a corresponding preset temperature threshold;
[0008] If it is determined that the temperature value of a certain circuit subcomponent is greater than the corresponding preset temperature threshold, the circuit subcomponent is determined to be an abnormal circuit component, and an alarm message is output to the user to remind the user to take corresponding control processing operations for the abnormal circuit component.
[0009] As an optional implementation, in the first aspect of the present invention, the unmanned detector is equipped with a plurality of sensor devices, and the sensor devices include: the unmanned detector is equipped with a plurality of sensor devices, and the sensor devices include: at least one of an image acquisition device, a temperature measurement device, and a positioning device;
[0010] Among them, the image acquisition device is used to identify and acquire target image data of the main line components of the line section to be inspected, the temperature measuring device is used to detect the temperature values of all line sub-components, and the positioning device is used to locate the line section to be inspected.
[0011] As an optional implementation, in the first aspect of the present invention, the identification result includes component positions and component types of multiple line subcomponents of the line sections, and the line subcomponents of the line sections are connection fittings;
[0012] Determining whether the temperature value of each circuit subcomponent is greater than the corresponding preset temperature threshold includes:
[0013] Classifying the temperature values of all detected circuit subcomponents according to the component types of the circuit subcomponents in the circuit section, and determining whether the temperature value of the circuit subcomponent of each component type is greater than a preset temperature threshold corresponding to the component type; and / or,
[0014] The temperature values of all detected circuit sub-components are classified and processed according to the component positions of the circuit sub-components in the circuit section, and it is determined whether the temperature value of the circuit sub-component of each component type is greater than a preset temperature threshold corresponding to the component position.
[0015] As an optional implementation, in the first aspect of the present invention, the deep learning network is a fast region generation convolutional neural network (Faster-R-CNN), and the fast region generation convolutional neural network includes: a region generation convolutional neural network (Fast-R-CNN), a region generation network (RPN), a region of interest pooling layer (Rol Pooling), and a classification and regression (Classification and Regression);
[0016] Among them, the region generation convolutional neural network includes multiple network layers, including Conv convolutional layer, ReLU activation function layer, Pooling layer, the region generation convolutional neural network is used to extract the feature value of the target image data, the region generation network is used to generate the selected area position of the line sub-component in the target image data, the interest domain pooling layer is used to collect the coordinates of the selected area generated by the region generation network and generate a proposal feature map (proposals feature maps), and the classification regressor is used to calculate the component type and final component position of the line sub-component of the target image data according to the proposal feature map.
[0017] As an optional implementation, in the first aspect of the present invention, the identification result further includes a location where a corresponding line subcomponent in the line main component is missing and / or damaged;
[0018] After receiving the target image data sent by the unmanned detector and identifying the target image data through a deep learning network, the method further includes:
[0019] The type of the corresponding missing and / or damaged line sub-component line is determined based on the position where the corresponding line sub-component in the line main component is missing and / or damaged, and an alarm message of the missing and / or damaged line sub-component is output to the user to remind the user to take control processing operations corresponding to the position where the line sub-component is missing and / or damaged.
[0020] As an optional implementation, in the first aspect of the present invention, the collecting of target image data of the main component of the line includes:
[0021] Adjust the final imaging parameters of the unmanned detector according to the imaging size, imaging position and imaging clarity of the main component of the line, and collect high-definition target image data of the main component of the line according to the imaging parameters;
[0022] The camera parameters include at least one of a camera angle, a camera position, and a camera lens parameter;
[0023] Outputting warning information to the user to remind the user to take a control processing operation corresponding to the line subcomponent includes:
[0024] Positioning the abnormal route component according to the positioning device of the unmanned detector to obtain the geographical location information of the abnormal route component;
[0025] The geographical location information sent by the unmanned detector is received, and warning information including the geographical location information is output to the user to remind the user to take corresponding control processing operations on the abnormal line component.
[0026] As an optional implementation, in the first aspect of the present invention, before collecting target image data of the line section to be detected by the unmanned detector, the method further includes:
[0027] Presetting the detection route of the unmanned detector according to the line section to be detected, so that the unmanned detector automatically identifies and collects target image data of the line components at corresponding positions in the line section to be detected according to the detection route;
[0028] After the target image data is identified by the deep learning network and an identification result is obtained, the method further includes:
[0029] Detecting whether the line subcomponents of the line section in the recognition result are in an overlapping state;
[0030] If it is detected that at least two line subcomponents are in an overlapping state, the unmanned detector is controlled to adjust the recognition position of the unmanned detector to a recognition position where the line subcomponents do not overlap with each other, and the image data of the line subcomponents are recaptured.
[0031] The second aspect of the present invention discloses a line component identification and alarm system based on an unmanned detector, the system comprising:
[0032] A first identification module is used to identify the main line components of the line section to be detected;
[0033] An acquisition module, used for acquiring target image data of the main circuit component identified by the first identification module;
[0034] A receiving module, used for receiving the target image data collected by the collecting module and sent by the unmanned detector;
[0035] A second recognition module is used to recognize the target image data received by the receiving module through a deep learning network to obtain a recognition result, wherein the recognition result includes a plurality of line sub-components of the line sections;
[0036] A first detection module is used to detect the temperature values of all circuit sub-components obtained by the second recognition module identifying the target image acquired by the acquisition module;
[0037] The receiving module is further used to receive the temperature values of all circuit sub-components detected by the first detection module and sent by the unmanned detector;
[0038] A judging module, used to judge whether the temperature value of each circuit sub-component received by the receiving module is greater than the corresponding preset temperature threshold;
[0039] The output module is used to determine that a certain circuit sub-component is an abnormal circuit component when the judgment module determines that the temperature value of the circuit sub-component is greater than the corresponding preset temperature threshold, and output alarm information to the user to remind the user to take corresponding control processing operations for the abnormal circuit component.
[0040] As an optional implementation, in the second aspect of the present invention, the unmanned detector is equipped with a plurality of sensor devices, and the sensor devices include: at least one of an image acquisition device, a temperature measurement device, and a positioning device;
[0041] Among them, the image acquisition device is used to identify and acquire target image data of the main line components of the line section to be inspected, the temperature measuring device is used to detect the temperature values of all line sub-components, and the positioning device is used to locate the line section to be inspected.
[0042] As an optional implementation, in the second aspect of the present invention, the identification result includes component positions and component types of multiple line sub-components of the line sections, and the line sub-components of the line sections are connection fittings;
[0043] The specific method in which the judgment module judges whether the temperature value of each circuit sub-component is greater than the corresponding preset temperature threshold is:
[0044] Classifying the temperature values of all detected circuit subcomponents according to the component types of the circuit subcomponents in the circuit section, and determining whether the temperature value of the circuit subcomponent of each component type is greater than a preset temperature threshold corresponding to the component type; and / or,
[0045] The temperature values of all detected circuit sub-components are classified and processed according to the component positions of the circuit sub-components in the circuit section, and it is determined whether the temperature value of the circuit sub-component of each component type is greater than a preset temperature threshold corresponding to the component position.
[0046] As an optional implementation, in the second aspect of the present invention, the deep learning network is a fast region generation convolutional neural network (Faster-R-CNN), and the fast region generation convolutional neural network includes: a region generation convolutional neural network (Fast-R-CNN), a region generation network (RPN), a region of interest pooling layer (Rol Pooling), and a classification and regression (Classification and Regression);
[0047] Among them, the region generation convolutional neural network includes multiple network layers, including Conv convolutional layer, ReLU activation function layer, Pooling layer, the region generation convolutional neural network is used to extract the feature value of the target image data, the region generation network is used to generate the selected area position of the line sub-component in the target image data, the interest domain pooling layer is used to collect the coordinates of the selected area generated by the region generation network and generate a proposal feature map (proposals feature maps), and the classification regressor is used to calculate the component type and final component position of the line sub-component of the target image data according to the proposal feature map.
[0048] As an optional implementation, in the second aspect of the present invention, the identification result further includes a location where a corresponding line subcomponent in the line main component is missing and / or damaged;
[0049] After the receiving module receives the target image data sent by the unmanned detector and identifies the target image data through a deep learning network, the system further includes:
[0050] A determination module, used to determine the type of the corresponding missing and / or damaged line sub-component line according to the position where the corresponding line sub-component in the line main component is missing and / or damaged;
[0051] The output module is further used to output alarm information of missing and / or damaged line subcomponents to the user, so as to remind the user to take control processing operations corresponding to the position where the line subcomponents are missing and / or damaged.
[0052] As an optional implementation, in the second aspect of the present invention, the specific manner in which the acquisition module acquires the target image data of the line main component is:
[0053] Adjust the final imaging parameters of the unmanned detector according to the imaging size, imaging position and imaging clarity of the main component of the line, and collect high-definition target image data of the main component of the line according to the imaging parameters;
[0054] The camera parameters include at least one of a camera angle, a camera position, and a camera lens parameter;
[0055] The output module outputs warning information to the user to remind the user to take a specific control processing operation corresponding to the line subcomponent:
[0056] Positioning the abnormal route component according to the positioning device of the unmanned detector to obtain the geographical location information of the abnormal route component;
[0057] The geographical location information sent by the unmanned detector is received, and warning information including the geographical location information is output to the user to remind the user to take corresponding control processing operations on the abnormal line component.
[0058] As an optional implementation, in the second aspect of the present invention, before the acquisition module acquires the target image data of the line section to be detected, the system further includes:
[0059] A preset module, used for presetting the detection route of the unmanned detector according to the line section to be detected, so that the unmanned detector automatically identifies and collects target image data of the line components at corresponding positions in the line section to be detected according to the detection route;
[0060] After the second recognition module recognizes the target image data through the deep learning network and obtains a recognition result, the system further includes:
[0061] A second detection module, used for detecting whether the line sub-components of the line section in the recognition result obtained by the second recognition module are in an overlapping state;
[0062] a control module, configured to control the unmanned detector to adjust the identification position of the unmanned detector to an identification position where the circuit sub-components do not overlap each other, if the detection module detects that at least two circuit sub-components are in an overlapping state;
[0063] The acquisition module is also used to acquire image data of the circuit sub-component.
[0064] The third aspect of the present invention discloses an unmanned detector, which is used to execute the line component identification and alarm method based on the unmanned detector disclosed in the first aspect of the present invention.
[0065] The fourth aspect of the present invention discloses another line component identification and alarm system based on unmanned detectors, the system comprising:
[0066] A memory storing executable program code;
[0067] a processor coupled to the memory;
[0068] The processor calls the executable program code stored in the memory to execute part or all of the steps in the line component identification and alarm method based on unmanned detectors disclosed in the first aspect of the present invention.
[0069] The fifth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the line component identification and alarm method based on unmanned detectors disclosed in the first aspect of the present invention.
[0070] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: a line component identification and alarm method and system based on an unmanned detector are provided, and the line component identification and alarm method based on an unmanned detector comprises: identifying the line main components of the line section to be detected by the unmanned detector and collecting the target image data of the line main components, receiving the target image data sent by the unmanned detector, and identifying the target image data by a deep learning network to obtain an identification result, wherein the identification result includes line sub-components of multiple line sections, detecting the temperature values of all line sub-components by the unmanned detector, and receiving the temperature values of all line sub-components sent by the unmanned detector, judging whether the temperature value of each line sub-component is greater than the corresponding preset temperature threshold, and if it is judged that the temperature value of a certain line sub-component is greater than the corresponding preset temperature threshold, determining that the line sub-component is an abnormal line component, and outputting an alarm message to the user to remind the user to take corresponding control processing operations for the abnormal line component. The implementation of the present invention can utilize unmanned detectors to accurately identify and collect target images of main line components on a line section, and accurately identify subcomponents of the main line components through a deep learning network, thereby improving the recognition efficiency and accuracy of the line, thereby facilitating improving the efficiency and accuracy of line fault detection; the temperature of subcomponents of the main line components is detected by unmanned detectors, and it is determined whether it exceeds a preset temperature threshold. If it exceeds the preset temperature threshold, the subcomponent is determined to be an abnormal line component, and an alarm message is output to the user. The status of line components at various locations can be monitored in real time and quickly, and when a certain line component fails, the user can be quickly informed to take corresponding measures, which is further conducive to improving the efficiency and accuracy of line fault detection. BRIEF DESCRIPTION OF THE DRAWINGS
[0071] In order to more clearly illustrate the technical solutions in 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 only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0072] Figure 1 It is a flow chart of a line component identification and alarm method based on an unmanned detector disclosed in an embodiment of the present invention;
[0073] Figure 2It is a flow chart of another method for identifying and warning line components based on unmanned detectors disclosed in an embodiment of the present invention;
[0074] Figure 3 It is a structural schematic diagram of a line component identification and alarm system based on an unmanned detector disclosed in an embodiment of the present invention;
[0075] Figure 4 It is a structural schematic diagram of another line component identification and alarm system based on unmanned detectors disclosed in an embodiment of the present invention;
[0076] Figure 5 It is a structural schematic diagram of an unmanned detector disclosed in an embodiment of the present invention;
[0077] Figure 6 It is a structural schematic diagram of another line component identification and alarm system based on unmanned detectors disclosed in an embodiment of the present invention. DETAILED DESCRIPTION
[0078] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme 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 only 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.
[0079] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.
[0080] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0081] The present invention discloses a line component identification and alarm method and system based on an unmanned detector, which can accurately identify and collect target images of the main line components on the line section by using the unmanned detector, and accurately identify the subcomponents of the main line components through a deep learning network, thereby improving the recognition efficiency and accuracy of the line, thereby facilitating the improvement of the efficiency and accuracy of line fault detection; the temperature of the subcomponents of the main line components is detected by the unmanned detector, and it is determined whether it exceeds the preset temperature threshold. If it exceeds the preset temperature threshold, the subcomponent is determined to be an abnormal line component, and an alarm information is output to the user, so that the status of the line components at various positions can be monitored in real time and quickly, and the user can be quickly informed to take corresponding measures when a certain line component fails, which is further conducive to improving the efficiency and accuracy of line fault detection. The following are detailed descriptions.
[0082] Embodiment 1
[0083] See also Figure 1 , Figure 1 This is a flow chart of a line component identification and alarm method based on an unmanned detector disclosed in an embodiment of the present invention. Figure 1 The described line component identification and alarm method based on unmanned detectors can be applied to unmanned detectors and line component identification and alarm systems based on unmanned detectors, wherein the unmanned detectors can be applied to the system, and the line component identification and alarm system based on unmanned detectors can be a local line component identification and alarm system based on unmanned detectors, or a line component identification and alarm cloud platform, which is not limited in the embodiments of the present invention. Figure 1 As shown, the line component identification and alarm method based on unmanned detector may include the following operations:
[0084] 101. Identify the main line components of the line section to be inspected through an unmanned detector, and collect target image data of the main line components.
[0085] In the embodiment of the present invention, optionally, the movement mode of the unmanned probe may include at least one of a flight mode, a land mode, and the like.
[0086] In the embodiment of the present invention, the unmanned detector is optionally equipped with multiple sensing devices, and the sensing devices may include at least one of an image acquisition device, a temperature measuring device, a positioning device, etc. Among them, the image acquisition device is used to identify and acquire the target image data of the main line components of the line section to be detected, the temperature measuring device is used to detect the temperature values of all line sub-components, and the positioning device is used to locate the line section to be detected. Further, the image acquisition device may include a camera module, an image recognition module, and an angle adjustment module, the temperature measuring device may include at least one of a thermal infrared thermometer, a resistance thermometer, a thermocouple thermometer, etc., and the positioning device may include at least one of a GPS satellite positioning device, a WiFi positioning device, a UWB positioning device, etc. In this way, the unmanned detector identifies and detects the line components through a variety of motion modes and sensing devices, enriching the identification and detection methods of the line components, thereby facilitating the improvement of the efficiency and accuracy of line fault troubleshooting.
[0087] In the embodiment of the present invention, optionally, collecting target image data of the main component of the line may include:
[0088] The final camera parameters of the unmanned detector are adjusted according to the imaging size, imaging position and imaging clarity of the main components of the line, and high-definition target image data of the main components of the line are collected according to the camera parameters. The camera parameters include at least one of the camera angle, camera position and camera lens parameters. Furthermore, the camera parameters may include at least one of the aperture parameters, shutter parameters, exposure parameters, white balance parameters and the like.
[0089] In this optional embodiment, further optionally, the method may also include the following operations:
[0090] When it is detected that the current detection time of the unmanned detector is nighttime, the camera parameters of the unmanned detector are adjusted to a nighttime camera mode.
[0091] Alternatively, when it is detected that the light brightness of the current detection environment of the unmanned detector is less than a preset light brightness threshold (for example, on a rainy day), the camera parameters of the unmanned detector are adjusted to a rainy day camera mode.
[0092] In this way, the main components of the line section that needs to be inspected can be identified by unmanned detectors, and target image data of the main components of the line can be collected. The detection method is automated, and the camera parameters of the unmanned detectors are adjusted in real time according to changes in the environment to collect clearer image data, which is conducive to improving the efficiency and accuracy of line fault detection.
[0093] 102. Receive target image data sent by the unmanned detector, and recognize the target image data through a deep learning network to obtain a recognition result, where the recognition result includes target line sub-components of multiple line main components.
[0094] In an embodiment of the present invention, optionally, the deep learning network is a fast region generation convolutional neural network (Faster-R-CNN), and the fast region generation convolutional neural network includes: a region generation convolutional neural network (Fast-R-CNN), a region generation network (RPN), a region of interest pooling layer (Rol Pooling), and a classification and regression (Classification and Regression).
[0095] Among them, the region generation convolutional neural network includes multiple network layers, including Conv convolutional layer, ReLU activation function layer, Pooling layer, the region generation convolutional neural network is used to extract the feature values of the target image data of the main components of the line, the region generation network is used to generate the selection position of the line sub-components in the target image data, the interest domain pooling layer is used to collect the coordinates of the selection generated by the region generation network and generate the selection feature map (Poposals Feature Maps), and the classification regressor is used to calculate the component type and final component position of the line sub-component of the target image data according to the selection feature map.
[0096] In an embodiment of the present invention, optionally, the recognition result may include component positions and component types of multiple line sub-components of the line section, and the line sub-components of the line section may be connection fittings. Among them, connection fittings can be defined as fittings used for connection or repair between conductors (ground) wires, and can meet certain mechanical and electrical performance requirements of conductors (ground). Furthermore, the recognition result may also include the component numbers of the line sub-components of the line section. In this way, the various small line sub-components contained in the main components of the line in the target image data are further accurately identified through the fast region generation convolutional neural network (Faster-R-CNN), which is conducive to improving the efficiency and accuracy of line fault troubleshooting.
[0097] 103. Detect the temperature values of all circuit sub-components through unmanned detectors, and receive the temperature values of all circuit sub-components sent by the unmanned detectors, and determine whether the temperature value of each circuit sub-component is greater than the corresponding preset temperature threshold. If it is determined that the temperature value of a certain circuit sub-component is greater than the corresponding preset temperature threshold, step 104 can be executed.
[0098] In the embodiment of the present invention, optionally, if it is determined that the temperature value of a certain circuit sub-component is less than or equal to the corresponding preset temperature threshold, step 101 may be re-executed.
[0099] In the embodiment of the present invention, optionally, the temperature values of all circuit sub-components can be detected by a temperature measuring device installed by an unmanned detector.
[0100] In the embodiment of the present invention, optionally, determining whether the temperature value of each circuit sub-component is greater than the corresponding preset temperature threshold may include:
[0101] Classifying the temperature values of all detected line subcomponents according to the component types of the line subcomponents in the line section, and determining whether the temperature value of the line subcomponent of each component type is greater than a preset temperature threshold value of the corresponding component type; and / or,
[0102] The temperature values of all detected line sub-components are classified and processed according to the component positions of the line sub-components in the line section, and it is determined whether the temperature value of the line sub-component of each component type is greater than the preset temperature threshold of the corresponding component position. In this way, when the temperature of all line sub-components is detected by the unmanned detector and it is determined whether each line sub-component is greater than the corresponding preset temperature threshold, it is beneficial to quickly detect the abnormal state of the line sub-components in the line section, thereby improving the efficiency and accuracy of line fault detection.
[0103] 104. Determine that the line subcomponent is an abnormal line component, and output warning information to the user to remind the user to take corresponding control processing operations for the abnormal line component.
[0104] In the embodiment of the present invention, optionally, outputting warning information to the user to remind the user to take a control processing operation corresponding to the line subcomponent may include:
[0105] The abnormal route component is located according to the positioning device of the unmanned detector to obtain the geographical location information of the abnormal route component.
[0106] Receive geographic location information sent by unmanned detectors, and output alarm information containing geographic location information to users to remind users to take corresponding control processing operations for abnormal line components.
[0107] The alarm information may also include at least one of the location information of the abnormal line component, the component type of the abnormal line component, the component number of the abnormal line component, the line section number of the abnormal line, the abnormal type of the abnormal line component, the abnormal level of the abnormal line component, etc. In this way, the temperature is detected by the unmanned detector and the abnormal line component among all line subcomponents is determined, and the geographical location information of the abnormal line component is determined by the unmanned detector, and the alarm information containing the geographical location information is sent to the user, so as to quickly and accurately find the corresponding abnormal line component and take corresponding processing measures, which is conducive to improving the efficiency and accuracy of line fault detection.
[0108] In an optional embodiment, the identification result may also include the location where the corresponding line sub-component in the line main component is missing and / or damaged.
[0109] In this optional embodiment, after receiving the target image data sent by the unmanned detector and identifying the target image data through the deep learning network, the method may further include the following operations:
[0110] The type of the corresponding missing and / or damaged line sub-component line is determined based on the position where the corresponding line sub-component in the line main component is missing and / or damaged, and an alarm message of the missing and / or damaged line sub-component is output to the user to remind the user to take control processing operations corresponding to the position where the line sub-component is missing and / or damaged.
[0111] It can be seen that this optional embodiment can determine the type of the corresponding missing and / or damaged line sub-component line according to the position where the corresponding line sub-component in the line main component is missing and / or damaged, and output alarm information of the missing and / or damaged line sub-component to the user, reminding the user to take corresponding processing measures, thereby enriching the detection method of abnormal positions of line sections, which is conducive to improving the efficiency and accuracy of line fault troubleshooting.
[0112] In another optional embodiment, before collecting the target image data of the line section to be detected by the unmanned detector, the method may further include the following operations:
[0113] The detection route and / or detection period of the unmanned detector is preset according to the line section to be detected, so that the unmanned detector automatically identifies and collects target image data of the line section to be detected and / or the line components at corresponding positions within the detection period according to the detection route.
[0114] It can be seen that this optional embodiment can preset the detection route of the unmanned detector, so that it can automatically identify and collect target image data of line components at corresponding positions in the line section that needs to be detected according to the detection route, thereby improving the detection efficiency and detection flexibility, which is conducive to improving the efficiency and accuracy of line fault troubleshooting.
[0115] Embodiment 2
[0116] See also Figure 2 , Figure 2 This is a flow chart of a line component identification and alarm method based on an unmanned detector disclosed in an embodiment of the present invention. Figure 2 The described line component identification and alarm method based on unmanned detectors can be applied to unmanned detectors and line component identification and alarm systems based on unmanned detectors, wherein the unmanned detectors can be applied to the system, and the line component identification and alarm system based on unmanned detectors can be a local line component identification and alarm system based on unmanned detectors, or a line component identification and alarm cloud platform, which is not limited in the embodiments of the present invention. Figure 2As shown, the line component identification and alarm method based on unmanned detector may include the following operations:
[0117] 201. Identify the main line components of the line section to be inspected by an unmanned detector, and collect target image data of the main line components.
[0118] 202. Receive target image data sent by the unmanned detector, and recognize the target image data through a deep learning network to obtain a recognition result, where the recognition result includes target line sub-components of multiple line main components.
[0119] 203 , detecting whether the line sub-components of the line section in the recognition result are in an overlapping state. If it is detected that at least two line sub-components are in an overlapping state, step 204 may be executed.
[0120] In the embodiment of the present invention, if no overlap between two circuit sub-components is detected in the recognition result, step 205 is executed.
[0121] 204. Control the unmanned detector to adjust the recognition position of the unmanned detector to a recognition position where the line sub-components do not overlap with each other, and re-collect image data of the line sub-components.
[0122] 205. Detect the temperature values of all circuit sub-components through unmanned detectors, and receive the temperature values of all circuit sub-components sent by the unmanned detectors, and determine whether the temperature value of each circuit sub-component is greater than the corresponding preset temperature threshold. If it is determined that the temperature value of a certain circuit sub-component is greater than the corresponding preset temperature threshold, step 206 can be executed.
[0123] 206. Determine that the line subcomponent is an abnormal line component, and output warning information to the user to remind the user to take corresponding control processing operations for the abnormal line component.
[0124] In the embodiment of the present invention, it should be noted that for the description of steps 201-202 and 205-206, please refer to steps 101-104 in the first embodiment, which will not be described in detail in the embodiment of the present invention.
[0125] It can be seen that the embodiment of the present invention can also detect whether the line sub-components of the line section in the identification result are in an overlapping state. If it is detected that there are at least two line sub-components in an overlapping state, the identification position of the unmanned detector is adjusted to a position where the line sub-components do not overlap with each other, and more accurate and clear image data of the line sub-components are re-collected to avoid the problem of incorrect determination or omission of abnormal line components due to incorrect temperature measurement of certain line sub-components, which is conducive to further improving the efficiency and accuracy of line fault troubleshooting.
[0126] It can be seen that implementation Figure 2 The described method accurately identifies and collects target images of main line components on a line section through an unmanned detector, and accurately identifies subcomponents of the main line components through a deep learning network, thereby improving the recognition efficiency and accuracy of the line, thereby facilitating the improvement of the efficiency and accuracy of line fault detection; the temperature of subcomponents of the main line components is detected by the unmanned detector, and it is determined whether it exceeds a preset temperature threshold. If it exceeds the preset temperature threshold, the subcomponent is determined to be an abnormal line component, and an alarm message is output to the user, so that the conditions of line components at various positions can be monitored in real time and quickly, and when a certain line component fails, the user can be quickly informed to take corresponding measures, thereby facilitating the improvement of the efficiency and accuracy of line fault detection; it can also detect whether the line subcomponents of the line section in the recognition result are in an overlapping state. If it is detected that at least two line subcomponents are in an overlapping state, the recognition position of the unmanned detector is adjusted to a position where the line subcomponents do not overlap with each other, and more accurate and clear image data of the line subcomponents are re-collected, so as to avoid the problem of erroneous confirmation or missed confirmation of abnormal line components due to incorrect temperature measurement of some line subcomponents, thereby facilitating the improvement of the efficiency and accuracy of line fault detection.
[0127] Embodiment 3
[0128] See also Figure 3 , Figure 3 1 is a schematic diagram of a circuit component identification and alarm system based on an unmanned detector disclosed in an embodiment of the present invention. Figure 3 The unmanned detector and the line component identification and alarm system based on the unmanned detector described above can execute the line component identification and alarm method based on the unmanned detector, and the unmanned detector can be applied to the line component identification and alarm system based on the unmanned detector (line component identification and alarm platform). The line component identification and alarm system based on the unmanned detector can be a local line component identification and alarm system based on the unmanned detector, or it can be a line component identification and alarm cloud platform, which is not limited in the embodiments of the present invention. Figure 3 As shown, the device may include: a first recognition module 301, a collection module 302, a receiving module 303, a second recognition module 304, a detection module 305, a judgment module 306, and an output module 307, wherein:
[0129] The first identification module 301 is used to identify the main line components of the line section to be detected.
[0130] The acquisition module 302 is used to acquire the target image data of the main components of the circuit identified by the first recognition module 301.
[0131] The receiving module 303 is used to receive the target image data collected by the collecting module 302 and sent by the unmanned detector.
[0132] The second recognition module 304 is used to recognize the target image data received by the receiving module 303 through a deep learning network to obtain a recognition result, which includes line sub-components of multiple line sections.
[0133] The first detection module 305 is used to detect the temperature values of all circuit sub-components obtained by the second recognition module 304 recognizing the target image collected by the collection module 302 .
[0134] The receiving module 303 is also used to receive the temperature values of all the line sub-components detected by the first detection module 305 and sent by the unmanned detector.
[0135] The judging module 306 is used to judge whether the temperature value of each circuit sub-component received by the receiving module 303 is greater than the corresponding preset temperature threshold.
[0136] The output module 307 is used to determine that the circuit subcomponent is an abnormal circuit component when the judgment module 306 determines that the temperature value of a circuit subcomponent is greater than the corresponding preset temperature threshold, and output alarm information to the user to remind the user to take corresponding control processing operations for the abnormal circuit component.
[0137] It can be seen that implementation Figure 3 The described line component identification and alarm system based on unmanned detectors accurately identifies and collects target images of main line components on the line section without the use of human detectors, and accurately identifies subcomponents of the main line components through a deep learning network, thereby improving the recognition efficiency and accuracy of the line, which is conducive to improving the efficiency and accuracy of line fault detection; the temperature of subcomponents of the main line components is detected by unmanned detectors, and it is determined whether it exceeds a preset temperature threshold. If it exceeds the preset temperature threshold, the subcomponent is determined to be an abnormal line component, and an alarm information is output to the user. It can monitor the status of line components at various locations in real time and quickly, and when a line component fails, the user can be quickly informed to take corresponding measures, which is further conducive to improving the efficiency and accuracy of line fault detection.
[0138] In an optional embodiment, the unmanned detector is equipped with a plurality of sensor devices, and the sensor devices include at least one of an image acquisition device, a temperature measurement device, and a positioning device.
[0139] Among them, the image acquisition device is used to identify and acquire the target image data of the main line components of the line section to be inspected, the temperature measuring device is used to detect the temperature values of all line sub-components, and the positioning device is used to locate the line section to be inspected.
[0140] It can be seen that the line component identification and alarm system based on unmanned detectors described in this optional embodiment identifies and detects line components through multiple sensing devices, enriching the identification and detection methods of line components, which is beneficial to improving the efficiency and accuracy of line fault troubleshooting.
[0141] In another optional embodiment, the identification result includes component positions and component types of multiple line sub-components of the line section, and the line sub-components of the line section are connection fittings.
[0142] And, if Figure 4 As shown, the specific manner in which the judgment module 306 judges whether the temperature value of each circuit sub-component is greater than the corresponding preset temperature threshold is:
[0143] The temperature values of all detected circuit sub-components are classified and processed according to the component types of the circuit sub-components in the circuit section, and it is determined whether the temperature value of the circuit sub-component of each component type is greater than a preset temperature threshold of the corresponding component type.
[0144] And / or, classify the temperature values of all detected circuit subcomponents according to the component positions of the circuit subcomponents in the circuit section, and determine whether the temperature value of the circuit subcomponent of each component type is greater than a preset temperature threshold of the corresponding component position.
[0145] It can be seen that implementation Figure 4 The described line component identification and alarm system based on unmanned detectors detects the temperature of all line sub-components through unmanned detectors and determines whether each line sub-component is greater than the corresponding preset temperature threshold, which is conducive to quickly detecting the abnormal state of the line sub-components in the line section, thereby facilitating improving the efficiency and accuracy of line fault troubleshooting.
[0146] In another optional embodiment, the deep learning network is a fast region generation convolutional neural network (Faster-R-CNN), which includes: a region generation convolutional neural network (Fast-R-CNN), a region generation network (RPN), a region of interest pooling layer (Rol Pooling), and a classification and regression (Classification and Regression).
[0147] Among them, the region generation convolutional neural network includes multiple network layers, including Conv convolutional layer, ReLU activation function layer, Pooling layer, the region generation convolutional neural network is used to extract the feature values of the target image data, the region generation network is used to generate the selection position of the line sub-component in the target image data, the interest domain pooling layer is used to collect the coordinates of the selection generated by the region generation network and generate the selection feature map (proposals feature maps), and the classification regressor is used to calculate the component type and the final component position of the line sub-component of the target image data according to the selection feature map.
[0148] It can be seen that the unmanned detector-based line component identification and alarm system described in this optional embodiment further accurately identifies various small line sub-components in the target image data through the fast region generation convolutional neural network (Faster-R-CNN), which is beneficial to improving the efficiency and accuracy of line fault troubleshooting.
[0149] In yet another optional embodiment, the identification result also includes the location where the corresponding line sub-component within the line main component is missing and / or damaged.
[0150] And, if Figure 4 As shown, after the receiving module 303 receives the target image data sent by the unmanned detector and recognizes the target image data through the deep learning network, the system also includes:
[0151] The determination module 308 is used to determine the type of the corresponding missing and / or damaged line sub-component line according to the position of the missing and / or damaged line sub-component in the line main component identified by the second identification module 304.
[0152] The output module 307 is also used to output to the user the alarm information of the line subcomponent missing and / or damaged determined by the determination module 308, so as to remind the user to take control processing operations corresponding to the position where the line subcomponent is missing and / or damaged.
[0153] It can be seen that implementation Figure 4 The described line component identification and alarm system based on unmanned detectors determines the type of the corresponding missing and / or damaged line sub-component line through the position of the missing and / or damaged line sub-component in the line main component, and outputs the alarm information of the missing and / or damaged line sub-component to the user, reminding the user to take corresponding processing measures, thereby enriching the detection method of abnormal positions of line sections, which is conducive to improving the efficiency and accuracy of line fault detection.
[0154] In yet another optional embodiment, Figure 4 As shown, the specific method of the acquisition module 302 to acquire the target image data of the main components of the line is:
[0155] The final imaging parameters of the unmanned detector are adjusted according to the imaging size, imaging position and imaging clarity of the main components of the line, and high-definition target image data of the main components of the line are collected according to the imaging parameters.
[0156] The camera parameters include at least one of a camera angle, a camera position, and a camera lens parameter.
[0157] The output module 307 outputs warning information to the user to remind the user to take specific control processing operations corresponding to the line subcomponent:
[0158] The abnormal route component is located according to the positioning device of the unmanned detector to obtain the geographical location information of the abnormal route component.
[0159] Receive geographic location information sent by unmanned detectors, and output alarm information containing geographic location information to users to remind users to take corresponding control processing operations on abnormal line components.
[0160] It can be seen that implementation Figure 4 The described line component identification and alarm system based on unmanned detectors identifies the main line components of the line section that needs to be inspected through unmanned detectors, and collects target image data of the main line components, automates the detection method, adjusts the camera parameters of the unmanned detectors in real time according to environmental changes to collect clearer image data, and determines the geographical location information of abnormal line components through unmanned detectors, and sends alarm information containing geographical location information to users, so as to quickly and accurately find the corresponding abnormal line components and take corresponding processing measures, which is conducive to improving the efficiency and accuracy of line fault troubleshooting.
[0161] In yet another optional embodiment, Figure 4 As shown, before the acquisition module 302 acquires the target image data of the line section to be detected, the system further includes:
[0162] The preset module 309 is used to preset the detection route of the unmanned detector according to the line section to be detected, so that the unmanned detector automatically identifies and collects target image data of the line components at corresponding positions in the line section to be detected according to the detection route.
[0163] After the second recognition module 304 recognizes the target image data through the deep learning network and obtains the recognition result, the system further includes:
[0164] The second detection module 310 is used to detect whether the line sub-components of the line segment in the recognition result obtained by the second recognition module 304 are in an overlapping state.
[0165] The control module 311 is used to control the unmanned detector to adjust the identification position of the unmanned detector to an identification position where the line sub-components do not overlap each other if the second detection module 310 detects that at least two line sub-components are in an overlapping state.
[0166] The acquisition module 302 is also used to acquire image data of the circuit sub-components.
[0167] It can be seen that implementation Figure 4 The described line component identification and alarm system based on unmanned detectors detects whether the line sub-components of the line section in the identification results are in an overlapping state. If it is detected that at least two line sub-components are in an overlapping state, the identification position of the unmanned detector is adjusted to a position where the line sub-components do not overlap with each other, and more accurate and clear image data of the line sub-components are re-collected to avoid the problem of incorrect determination or omission of abnormal line components due to incorrect temperature measurement of certain line sub-components, thereby helping to further improve the efficiency and accuracy of line fault detection.
[0168] Embodiment 4
[0169] Please refer to the figure, Figure 5 is a schematic diagram of the structure of an unmanned detector disclosed in an embodiment of the present invention. Figure 5 As shown, unmanned detectors can be used to achieve Figure 1 or Figure 2 The line component identification and alarm method based on unmanned detectors described in the embodiment is not limited in the embodiment of the present invention.
[0170] Embodiment 5
[0171] See also Figure 6 Figure 6 The present invention discloses a schematic diagram of a circuit component identification and alarm system based on an unmanned detector. Figure 6 The unmanned detector and the line component identification and alarm system based on the unmanned detector can execute the line component identification and alarm method based on the unmanned detector, and the unmanned detector can be applied to the line component identification and alarm system based on the unmanned detector (line component identification and alarm platform). The line component identification and alarm system based on the unmanned detector can be a local line component identification and alarm system based on the unmanned detector, or a line component identification and alarm cloud platform, which is not limited in the embodiments of the present invention. Figure 5 As shown, the system may include:
[0172] A memory 601 storing executable program codes;
[0173] a processor 602 coupled to the memory 601;
[0174] Furthermore, it may also include an input interface 603 and an output interface 604 coupled to the processor 602;
[0175] The processor 602 calls the executable program code stored in the memory 601 to execute part or all of the steps in the line component identification and alarm method based on unmanned detectors disclosed in the first or second embodiment of the present invention.
[0176] Embodiment 6
[0177] An embodiment of the present invention discloses a computer storable medium storing computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the line component identification and alarm method based on unmanned detectors disclosed in Embodiment 1 or Embodiment 2 of the present invention.
[0178] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.
[0179] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.
[0180] Finally, it should be noted that the line component identification and alarm method and device based on unmanned detectors disclosed in the embodiment of the present invention only discloses the preferred embodiments of the present invention, which are only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, ordinary technicians in this field should understand that it is still possible to modify the technical solutions recorded in the aforementioned embodiments, or to 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 various embodiments of the present invention.
Claims
1. A line component identification and alarm method based on unmanned detectors, characterized in that: The method comprises: Identifying the main line components of the line section to be inspected by an unmanned detector, and collecting target image data of the main line components; Receiving the target image data sent by the unmanned detector, and identifying the target image data through a deep learning network to obtain an identification result, wherein the identification result includes target line subcomponents of a plurality of the line main components; Detecting the temperature values of all circuit subcomponents by the unmanned detector, and receiving the temperature values of all circuit subcomponents sent by the unmanned detector, and determining whether the temperature value of each circuit subcomponent is greater than a corresponding preset temperature threshold; If it is determined that the temperature value of a certain circuit subcomponent is greater than the corresponding preset temperature threshold, the circuit subcomponent is determined to be an abnormal circuit component, and an alarm message is output to the user to remind the user to take corresponding control processing operations for the abnormal circuit component; Before collecting target image data of the main line components of the line section to be detected by the unmanned detector, the method further includes: Presetting the detection route of the unmanned detector according to the line section to be detected, so that the unmanned detector automatically identifies and collects target image data of the line components at corresponding positions in the line section to be detected according to the detection route; After the target image data is identified by the deep learning network and an identification result is obtained, the method further includes: Detecting whether the line subcomponents of the line section in the recognition result are in an overlapping state; If it is detected that at least two line subcomponents are in an overlapping state, the unmanned detector is controlled to adjust the recognition position of the unmanned detector to a recognition position where the line subcomponents do not overlap with each other, and the image data of the line subcomponents are recaptured.
2. The line component identification and alarm method based on unmanned detector according to claim 1 is characterized in that: The unmanned detector is equipped with multiple sensor devices, and the sensor devices include: at least one of an image acquisition device, a temperature measurement device, and a positioning device; Among them, the image acquisition device is used to identify and acquire target image data of the main line components of the line section to be inspected, the temperature measuring device is used to detect the temperature values of all line sub-components, and the positioning device is used to locate the line section to be inspected.
3. The line component identification and alarm method based on unmanned detector according to claim 1 or 2, characterized in that: The identification result includes component positions and component types of the line sub-components of the plurality of line sections, and the line sub-components of the line section are connection fittings; The determining whether the temperature value of each circuit sub-component is greater than the corresponding preset temperature threshold comprises: Classifying the temperature values of all detected line subcomponents according to the component types of the line subcomponents in the line section, and determining whether the temperature value of the line subcomponent of each component type is greater than a preset temperature threshold corresponding to the component type; and / or, The temperature values of all detected circuit sub-components are classified and processed according to the component positions of the circuit sub-components in the circuit section, and it is determined whether the temperature value of the circuit sub-component of each component type is greater than a preset temperature threshold corresponding to the component position.
4. The line component identification and alarm method based on unmanned detector according to claim 2 or 3, characterized in that: The deep learning network is a fast region generation convolutional neural network, which includes: a region generation convolutional neural network, a region generation network, an interest domain pooling layer, and a classification regressor; Among them, the region generation convolutional neural network includes multiple network layers, including Conv convolutional layer, ReLU activation function layer, Pooling layer, the region generation convolutional neural network is used to extract the feature value of the target image data, the region generation network is used to generate the selected area position of the line sub-component in the target image data, the interest domain pooling layer is used to collect the coordinates of the selected area generated by the region generation network and generate a selected area feature map, and the classification regressor is used to calculate the component type and final component position of the line sub-component of the target image data according to the selected area feature map.
5. The line component identification and alarm method based on unmanned detector according to claim 4 is characterized in that: The identification result also includes the location where the corresponding circuit sub-component in the circuit main component is missing and / or damaged; After receiving the target image data sent by the unmanned detector and identifying the target image data through a deep learning network, the method further includes: The type of the corresponding missing and / or damaged line sub-component line is determined based on the position where the corresponding line sub-component in the line main component is missing and / or damaged, and an alarm message of the missing and / or damaged line sub-component is output to the user to remind the user to take control processing operations corresponding to the position where the line sub-component is missing and / or damaged.
6. The line component identification and alarm method based on unmanned detector according to claim 2 or 5, characterized in that: The collecting of target image data of the main part of the line includes: Adjust the final imaging parameters of the unmanned detector according to the imaging size, imaging position and imaging clarity of the main component of the line, and collect high-definition target image data of the main component of the line according to the imaging parameters; The camera parameters include at least one of a camera angle, a camera position, and a camera lens parameter; Outputting warning information to the user to remind the user to take a control processing operation corresponding to the line subcomponent includes: Positioning the abnormal line component according to the positioning device of the unmanned detector to obtain the geographical location information of the abnormal line component; The geographical location information sent by the unmanned detector is received, and warning information including the geographical location information is output to the user to remind the user to take corresponding control processing operations on the abnormal line component.
7. A line component identification and alarm system based on unmanned detectors, characterized in that: The system comprises: A first identification module is used to identify the main line components of the line section to be detected; An acquisition module, used for acquiring target image data of the main circuit component identified by the first identification module; A receiving module, used for receiving the target image data collected by the collecting module and sent by the unmanned detector; A second recognition module is used to recognize the target image data received by the receiving module through a deep learning network to obtain a recognition result, wherein the recognition result includes a plurality of line sub-components of the line sections; A first detection module, used for detecting temperature values of all circuit sub-components obtained by the second recognition module identifying the target image data collected by the collection module; The receiving module is further used to receive the temperature values of all circuit sub-components detected by the first detection module and sent by the unmanned detector; A judging module, used to judge whether the temperature value of each circuit sub-component received by the receiving module is greater than the corresponding preset temperature threshold; An output module, configured to determine that a certain circuit sub-component is an abnormal circuit sub-component when the judgment module determines that the temperature value of the circuit sub-component is greater than the corresponding preset temperature threshold, and output alarm information to the user to remind the user to take corresponding control processing operations for the abnormal circuit sub-component; The system further comprises: A preset module is used to preset the detection route of the unmanned detector according to the line section to be detected before the acquisition module acquires the target image data of the line main component of the line section to be detected, so that the unmanned detector automatically identifies and acquires the target image data of the line component at the corresponding position in the line section to be detected according to the detection route; And, the system further comprises: A second detection module is used for detecting whether the line sub-components of the line section in the recognition result obtained by the second recognition module are in an overlapping state after the second recognition module recognizes the target image data through a deep learning network and obtains a recognition result; a control module, configured to control the unmanned detector to adjust the identification position of the unmanned detector to an identification position where the line sub-components do not overlap each other if the second detection module detects that at least two line sub-components are in an overlapping state; The acquisition module is also used to acquire image data of the circuit sub-component.
8. An unmanned detector, characterized in that: The unmanned detector is used to execute the line component identification and alarm method based on the unmanned detector as described in any one of claims 1-6.
9. A line component identification and alarm system based on unmanned detectors, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the line component identification and alarm method based on unmanned detectors as described in any one of claims 1-6.
