Insulation sheath inspection methods, devices, inspection robots, and storage media
By integrating electromagnetic measurement and image processing technologies into the inspection robot, abnormalities in the insulation sheath can be automatically identified, solving the problem of time-consuming and labor-intensive manual inspection and achieving efficient insulation sheath detection.
Patent Information
- Application Number
- CN202310338466.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-03-31
- Publication Date
- 2026-11-10
- Estimated Expiration
- 2043-03-31
AI Technical Summary
In the current technology, the inspection of insulation sheaths requires manual inspection, which is time-consuming, labor-intensive, and inefficient.
An inspection robot equipped with a camera, electromagnetic measuring device, and positioning module is used to automatically identify abnormalities in the insulation sheath through electromagnetic data acquisition and image processing, reducing human intervention.
It enables unmanned inspection, saving manpower and material resources, reducing image acquisition volume and model computing resources, and improving inspection efficiency.
Smart Images

Figure CN116404570B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of power equipment inspection technology, and in particular to an inspection method, device, inspection robot, and storage medium for insulating sheaths. Background Technology
[0002] Currently, to ensure the safety of overhead power lines, insulating sheaths are usually installed on the transmission lines to protect them.
[0003] After the insulation sleeve is installed, the installation condition needs to be inspected regularly. Currently, this is mainly done by visual inspection or by manually reviewing images taken by drones to determine whether there are any issues such as incomplete installation, detachment, or loose fixing structures on the insulation sleeve on the transmission line. This manual monitoring is time-consuming and labor-intensive. Summary of the Invention
[0004] This invention provides a method, device, inspection robot, and storage medium for inspecting insulating sheaths, in order to solve the problem that manual inspection of insulating sheaths is currently required, which is time-consuming and labor-intensive.
[0005] In a first aspect, the present invention provides a method for inspecting insulating sheaths, applicable to an inspection robot equipped with a camera, an electromagnetic measuring device, and a positioning module, comprising:
[0006] During the process of controlling the robot to walk on the power transmission line, electromagnetic data is collected through an electromagnetic measuring device.
[0007] When the electromagnetic data is greater than a preset threshold, the positioning module determines a first position, which is the position where electromagnetic data greater than the threshold is collected.
[0008] The robot is controlled to walk and collect an image at the first position on the power transmission line, and a second position is determined by the positioning module, the second position being the position when the image at the first position was collected;
[0009] The image is input into the insulation sheath anomaly detection model to obtain the detection result;
[0010] When the detection result indicates an abnormality in the insulation sheath, a notification message indicating an abnormality in the insulation sheath is sent to the system backend.
[0011] Optionally, during the process of the controlled robot walking on the power transmission line, electromagnetic data is collected through an electromagnetic measuring device, including:
[0012] While controlling the robot to walk on the power transmission line, electric field and magnetic field data are collected through electromagnetic measuring devices.
[0013] Optionally, when the electromagnetic data is greater than a preset threshold, the positioning module determines the first position, including:
[0014] When the electric field data is greater than a preset electric field data threshold, and / or the magnetic field data is greater than a preset magnetic field data threshold, the positioning module determines the first position.
[0015] Optionally, controlling the robot to walk and acquire an image at the first location on the power transmission line includes:
[0016] The walking distance is determined based on the first location and the calibration parameters of the camera;
[0017] When the distance between the robot's position and the first position is at least equal to the walking distance, the camera is controlled to capture images.
[0018] Optionally, the insulation sheath anomaly detection model includes an insulation sheath installation anomaly detection sub-model and an insulation sheath fixation anomaly detection sub-model. The step of inputting the image into the insulation sheath anomaly detection model to obtain the detection result includes:
[0019] The image is input into the insulation sheath installation anomaly detection sub-model to obtain the insulation sheath installation detection result;
[0020] The image is input into the insulation sheath fixation anomaly detection sub-model to obtain the insulation sheath fixation detection result.
[0021] Optionally, when the detection result indicates an abnormality in the insulation sheath, sending an alert message about the abnormality to the system backend includes:
[0022] When the insulation sleeve installation test result is an insulation sleeve installation abnormality, and / or the insulation sleeve fixation test result is an insulation sleeve fixation abnormality, the image and the second position are used to generate an insulation sleeve abnormality prompt message.
[0023] Optional, also includes:
[0024] When the electromagnetic data exceeds a preset threshold, an insulation performance abnormality warning message is generated using the electromagnetic data and sent to the system backend.
[0025] Secondly, the present invention provides an insulation sheath inspection device, applicable to an inspection robot equipped with a camera, an electromagnetic measuring device, and a positioning module, comprising:
[0026] The electromagnetic data acquisition module is used to collect electromagnetic data through an electromagnetic measuring device while controlling the robot to walk on the power transmission line.
[0027] The first positioning module is used to determine a first position when the electromagnetic data is greater than a preset threshold, wherein the first position is the position where electromagnetic data greater than the threshold is collected;
[0028] The image acquisition module is used to control the robot to walk and acquire an image at the first position on the power transmission line, and to determine a second position through the positioning module, wherein the second position is the position when the image at the first position was acquired;
[0029] The detection result prediction module is used to input the image into the insulation sheath anomaly detection model to obtain the detection result;
[0030] The notification message sending module is used to send a notification message indicating an abnormality in the insulation sheath to the system backend when the detection result indicates an abnormality in the insulation sheath.
[0031] Thirdly, the present invention provides an inspection robot, the inspection robot comprising:
[0032] The system includes a camera, a positioning module, an electromagnetic measuring device, at least one processor, and a memory. The camera, positioning module, electromagnetic measuring device, and memory are all connected to the at least one processor.
[0033] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the insulation sheath inspection method described in any one of the first aspects.
[0034] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the insulation sheath inspection method described in any of the first aspects of the present invention.
[0035] The inspection robot of this invention is equipped with a camera, a positioning module, and an electromagnetic measurement device. While moving along the power transmission line, the robot collects electromagnetic data using the electromagnetic measurement device. When the electromagnetic data exceeds a preset threshold, the positioning module determines a first position, which is the position where electromagnetic data exceeding the preset threshold is collected. The robot moves and collects an image at the first position on the power transmission line, and the positioning module determines a second position, which is the position where the image at the first position was collected. The image is input into an insulation sheath anomaly detection model to obtain a detection result. When the detection result indicates an insulation sheath anomaly, an alert message indicating an insulation sheath anomaly is sent to the system backend. This embodiment triggers image acquisition when electromagnetic data exceeds a preset threshold, inputs the image into the insulation sheath anomaly detection model to obtain a detection result, and sends an alert message to the system backend when the detection result indicates an insulation sheath anomaly. This eliminates the need for manual inspection of the insulation sheath, saving manpower and resources. Furthermore, determining whether to trigger image acquisition based on electromagnetic data reduces the amount of image acquisition and the computational resources of the model.
[0036] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description
[0037] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0038] Figure 1 This is a flowchart of an insulation sheath inspection method according to Embodiment 1 of the present invention;
[0039] Figure 2A This is a flowchart of an insulation sheath inspection method provided in Embodiment 2 of the present invention;
[0040] Figure 2B This is a schematic diagram of the first and second positions in an embodiment of the present invention;
[0041] Figure 3 This is a schematic diagram of the structure of an insulating sheath inspection device provided in Embodiment 3 of the present invention;
[0042] Figure 4 This is a schematic diagram of the inspection robot provided in Embodiment 4 of the present invention. Detailed Implementation
[0043] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.
[0044] Example 1
[0045] Figure 1 This is a flowchart of an insulation sheath inspection method provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation where an inspection robot is used to inspect the insulation sheaths on transmission lines. The method can be executed by an insulation sheath inspection device, which can be implemented in hardware and / or software and can be configured in the inspection robot. Figure 1 As shown, the method for inspecting insulating sheaths includes:
[0046] S101. During the process of controlling the robot to walk on the power transmission line, electromagnetic data is collected through an electromagnetic measuring device.
[0047] The inspection robot in this embodiment can be equipped with a camera, a positioning module, and an electromagnetic measurement device. The camera is a monocular, binocular, or multi-lens visible light camera used to collect images of the power transmission line. The positioning module can be a GPS or Beidou positioning module. The electromagnetic measurement device is used to collect electromagnetic data, which can include electric field data and magnetic field data. The electric field data can be the electric field strength, and the magnetic field data can be the magnetic field strength.
[0048] In this embodiment, an insulating sheath can be installed on the power transmission line. When the robot walks on the power transmission line to inspect the insulating sheath, the electromagnetic measuring device on the robot approaches the power transmission line to measure the intensity of the electromagnetic field radiated through the insulating sheath when the power transmission line is energized, and obtain electromagnetic data.
[0049] S102. When the electromagnetic data is greater than a preset threshold, the first position is determined by the positioning module. The first position is the position where electromagnetic data greater than the preset threshold is collected.
[0050] The robot is also equipped with a processor. After receiving electromagnetic data measured by the electromagnetic measuring device, the processor compares the electromagnetic data with a preset threshold. If the electromagnetic data is greater than the preset threshold, the positioning module determines a first position. This first position is the location of the robot when electromagnetic data exceeding the preset threshold is collected, which is the location on the power transmission line where the electromagnetic data is greater than the preset threshold. Electromagnetic data exceeding the preset threshold indicates that the insulation performance of the insulating sheath at this first position does not meet the standard and cannot shield the electromagnetic field generated by the energized power transmission line. This could be due to factors such as decreased insulation performance of the insulating sheath or improper installation.
[0051] In one embodiment, when the electromagnetic data exceeds a preset threshold, an insulation performance abnormality prompt message is generated using the electromagnetic data and sent to the system backend. For example, the insulation performance abnormality prompt message can be generated using electromagnetic data and a first location and sent to the system backend, so that backend personnel can determine whether the insulation performance is abnormal through the electromagnetic data and determine the location of the insulation performance abnormality through the first location, so as to dispatch maintenance personnel to perform maintenance.
[0052] S103. Control the robot to walk and collect images at the first position on the power transmission line, and determine the second position through the positioning module. The second position is the position when the image at the first position was collected.
[0053] If the electromagnetic data exceeds a preset threshold, the robot continues to move along the power line, capturing images of the power line at a first location using its onboard camera, and determining a second location using its positioning module. This second location is the position where the image from the first location was captured. This allows the robot to capture an image when the camera cannot capture an image at the first location, but after moving a certain distance until the power line at the first location enters the camera's field of view.
[0054] S104. Input the image into the insulation sheath anomaly detection model to obtain the detection result.
[0055] The insulation sheath anomaly detection model in this embodiment is used to detect insulation sheath installation anomalies and insulation sheath fixing anomalies. Insulation sheath installation anomalies may refer to the insulation sheath not completely covering the transmission line, insulation sheath damage, etc. Insulation sheath fixing anomalies may refer to the anomalies in the fixing structure that fixes the insulation sheath to the transmission line, such as loose cable ties, cable ties not being tied in the preset position, etc.
[0056] The insulation sheath anomaly detection model can be any neural network such as CNN, RNN, or DNN, and is pre-trained using images of insulation sheath installation anomalies and insulation sheath fixation anomalies as samples. After inputting the images into the trained insulation sheath anomaly detection model, detection results can be obtained, which can include insulation sheath installation being normal, insulation sheath installation being abnormal, insulation sheath fixation being normal, and insulation sheath fixation being abnormal.
[0057] S105. When the test result indicates that the insulation sheath is abnormal, send an error message to the system backend indicating that the insulation sheath is abnormal.
[0058] For example, when the detection result indicates abnormal installation and / or abnormal fixation of the insulation sleeve, the shielding effect of the insulation sleeve against the electromagnetic field will be reduced, and the transmission line will be at risk of leakage. An abnormal insulation sleeve prompt message containing the second location and the captured image can be generated and sent to the system backend, so that the system backend personnel can further determine whether the insulation sleeve is abnormal through the image. If so, maintenance personnel can be dispatched to the second location to maintain the insulation sleeve.
[0059] The inspection robot of this invention is equipped with a camera, a positioning module, and an electromagnetic measurement device. While moving along the power transmission line, the robot collects electromagnetic data using the electromagnetic measurement device. When the electromagnetic data exceeds a preset threshold, the positioning module determines a first position, which is the position where electromagnetic data exceeding the preset threshold is collected. The robot moves and collects an image at the first position on the power transmission line, and the positioning module determines a second position, which is the position where the image at the first position was collected. The image is input into an insulation sheath anomaly detection model to obtain a detection result. When the detection result indicates an insulation sheath anomaly, an alert message indicating an insulation sheath anomaly is sent to the system backend. This embodiment triggers image acquisition when electromagnetic data exceeds a preset threshold, inputs the image into the insulation sheath anomaly detection model to obtain a detection result, and sends an alert message to the system backend when the detection result indicates an insulation sheath anomaly. This eliminates the need for manual inspection of the insulation sheath, saving manpower and resources. Furthermore, determining whether to trigger image acquisition based on electromagnetic data reduces the amount of image acquisition and the computational resources of the model.
[0060] Example 2
[0061] Figure 2A This is a flowchart of an insulation sheath inspection method provided in Embodiment 2 of the present invention. This embodiment of the present invention is an optimization based on Embodiment 1 described above, such as... Figure 2A As shown, the method for inspecting insulating sheaths includes:
[0062] S201. During the process of controlling the robot to walk on the power transmission line, electric field data and magnetic field data are collected through electromagnetic measurement devices.
[0063] The electromagnetic measuring device in this embodiment can measure electric field data and magnetic field data. An insulating sheath is installed on the transmission line. When the robot walks on the transmission line to inspect the insulating sheath, the electromagnetic measuring device on the robot approaches the transmission line to measure the electric field intensity radiated through the insulating sheath when the transmission line is energized as electric field data, and the magnetic field intensity radiated by the transmission line as magnetic field data.
[0064] S202. When the electric field data is greater than a preset electric field data threshold and / or the magnetic field data is greater than a preset magnetic field data threshold, the first position is determined by the positioning module.
[0065] Specifically, when at least one of the electric field data and magnetic field data is greater than the corresponding threshold, it indicates that the performance of the insulating sheath has deteriorated, resulting in a decrease in the shielding performance of the insulating sheath against electric and magnetic fields. The electric and magnetic field strengths radiated through the insulating sheath by the transmission line are too high. For example, the insulating sheath may not be installed properly, may be broken, or may be loose. In this case, the positioning module locates the robot's current position to obtain a first position, which is the position on the transmission line where at least one of the electric field data and magnetic field data is detected to be greater than the corresponding threshold.
[0066] S203. Determine the walking distance based on the first position and the calibration parameters of the camera.
[0067] The calibration parameters of the camera can include parameters such as the camera's focal length, viewing angle, position in the robot, and pitch angle. Based on the imaging principle, the walking distance can be calculated using the first position and calibration parameters. When the distance the robot travels from the first position equals the walking distance, the power line at the first position enters the camera's field of view, and thus the camera can capture an image of the power line at the first position.
[0068] like Figure 2B As shown, the robot walks along the F direction on the power transmission line. At the first position A, it detects that the electromagnetic data is greater than the preset electromagnetic data threshold. After the robot walks to the second position B, it takes an image of the first position A. The distance between the first position A and the second position B is at least the walking distance D.
[0069] S204. When the distance between the robot's position and the first position is at least equal to the walking distance, control the camera to capture images.
[0070] Specifically, such as Figure 2B As shown, after the robot detects that the electromagnetic data at the first position A is greater than the preset electromagnetic data threshold, it controls the robot to continue walking a distance D along the F direction to reach the second position B. At the second position B, the power transmission line at the first position A enters the field of view of the robot's camera, and the camera can be controlled to capture images.
[0071] S205. The second position is determined by the positioning module. The second position is the position when the image of the first position was acquired.
[0072] Specifically, when the robot moves to the second position B, the positioning module can locate the second position.
[0073] S206. Input the image into the insulation sheath installation anomaly detection sub-model to obtain the insulation sheath installation detection result.
[0074] The insulation sheath installation anomaly detection sub-model in this embodiment is used to detect whether the insulation sheath installation is abnormal. In one embodiment, the insulation sheath installation anomaly detection sub-model is trained in advance based on the insulation sheath installation operation result image as training sample, that is, using operation images such as the insulation sheath being fully installed to cover the live bare conductor or the insulation sheath being loose and the live bare conductor being exposed.
[0075] The abnormal installation detection sub-model for the insulating sheath can be an image classification model, which can be a convolutional neural network (CNN). An initial CNN is trained to enable it to extract features from training samples effectively and to classify images. The basic structure of the CNN can include convolutional layers, pooling layers, and fully connected layers, with convolutional and pooling layers alternating. The convolutional layers extract features from training samples through convolution calculations, while the pooling layers downsample the training samples input to the CNN, reducing their size while retaining important information. The fully connected layers classify the images based on the image features determined by the convolutional layers.
[0076] Specifically, during the training phase, a large number of images of insulation sheath installation results are collected as training samples to train the neural network. During training, images are labeled as positive and negative samples. Positive samples are images of insulation sheath installation that is correct, while negative samples are images of abnormal installation, such as incomplete insulation sheath wrapping of the bare conductor or protrusions in the insulation sheath that are not in contact with the bare conductor. The ground truth value of each positive sample is marked as 1, and the ground truth value of each negative sample is marked as 0. Multiple labeled positive samples and multiple labeled negative samples are used to train the insulation sheath installation anomaly detection sub-model. After each training, the insulation sheath installation anomaly detection sub-model can be iteratively optimized by using a validation sample set and a loss function. Training of the insulation sheath installation anomaly detection sub-model is stopped when the preset accuracy is reached or the preset number of training rounds is reached.
[0077] After inputting the image into the insulation sheath installation anomaly detection sub-model, the insulation sheath installation detection result is obtained, which can be either a normal or abnormal insulation sheath installation result.
[0078] S207. Input the image into the insulation sheath fixation anomaly detection sub-model to obtain the insulation sheath fixation detection result.
[0079] The insulation sheath fixing anomaly detection sub-model in this embodiment is used to check whether the fixing structure of the insulation sheath is abnormal. Referring to the training process of the insulation sheath installation anomaly detection sub-model, a large number of images of normal and abnormal insulation sheath fixing can be collected as a training set to train the insulation sheath fixing anomaly detection sub-model. For example, if the insulation sheath is fixed to the transmission line by cable ties, images of the interface of the cable ties being only slightly in contact and not fully fastened can be collected. Or, images of the cable ties being only hanging on the working line and not closed can be collected.
[0080] After inputting the image into the insulation sheath fixation anomaly detection sub-model, the insulation sheath fixation detection result is obtained, which can be either a normal or abnormal insulation sheath fixation result.
[0081] S208. When the insulation sleeve installation test result is that the insulation sleeve installation is abnormal, and / or the insulation sleeve fixing test result is that the insulation sleeve fixing is abnormal, an insulation sleeve abnormality prompt message is generated using an image and a second location and sent to the system backend.
[0082] When the insulation sleeve installation test result is an abnormality, and / or the insulation sleeve fixation test result is an abnormality, an insulation sleeve abnormality prompt message can be generated from the image and the second location, and this prompt message can be sent to the system backend to remind backend personnel to further determine whether an insulation sleeve installation or fixation abnormality has occurred through the image. If so, the backend personnel will dispatch maintenance personnel to the second location to maintain the insulation sleeve.
[0083] In this embodiment, the robot collects electric and magnetic field data via an electromagnetic measurement device while moving along the power transmission line. When the electric field data exceeds a preset threshold and / or the magnetic field data exceeds a preset threshold, a first position is determined by the positioning module. The walking distance is determined based on the first position and the camera's calibration parameters. When the distance between the robot's position and the first position is at least equal to the walking distance, the camera is controlled to capture an image. A second position is then determined by the positioning module; this second position is the position where the image from the first position was captured. The image is input into an insulation sheath installation anomaly detection sub-model to obtain the insulation sheath installation detection result, and the image is also input into an insulation sheath fixation anomaly detection sub-model to obtain the insulation sheath fixation result. Based on the detection results, when the insulation sleeve installation detection result is an abnormality and / or the insulation sleeve fixation detection result is an abnormality, an abnormality prompt message is generated using images and a second location and sent to the system backend. In this embodiment, the acquisition of images is triggered when the electric field data and magnetic field data exceed the preset threshold of the response. The images are then input into the insulation sleeve installation abnormality detection sub-model and the insulation sleeve fixation abnormality detection sub-model, respectively, to obtain the insulation sleeve installation detection result and the insulation sleeve fixation detection result. This eliminates the need for manual inspection of the insulation sleeve, saving manpower and resources. Furthermore, by first determining whether to trigger image acquisition using electric field data and magnetic field data, the amount of image acquisition and the computational resources of the model are reduced.
[0084] Example 3
[0085] Figure 3 This is a schematic diagram of an insulating sheath inspection device provided in Embodiment 3 of the present invention. Figure 3 As shown, this insulation sheath inspection device is applied to an inspection robot equipped with a camera, electromagnetic measuring device, and positioning module, and includes:
[0086] The electromagnetic data acquisition module 301 is used to collect electromagnetic data through an electromagnetic measuring device during the process of controlling the robot to walk on the power transmission line.
[0087] The first positioning module 302 is used to determine a first position when the electromagnetic data is greater than a preset threshold, wherein the first position is the position where electromagnetic data greater than the threshold is collected;
[0088] The image acquisition module 303 is used to control the robot to walk and acquire an image at the first position on the power transmission line, and to determine a second position through the positioning module, wherein the second position is the position when the image at the first position was acquired;
[0089] The detection result prediction module 304 is used to input the image into the insulation sheath anomaly detection model to obtain the detection result;
[0090] The prompt message sending module 305 is used to send a prompt message indicating that the insulation sheath is abnormal to the system backend when the detection result indicates that the insulation sheath is abnormal.
[0091] Optionally, the electromagnetic data acquisition module 301 includes:
[0092] The data acquisition unit is used to collect electric field and magnetic field data through electromagnetic measuring devices while controlling the robot to walk on the power transmission line.
[0093] Optionally, the first positioning module 302 includes:
[0094] The first position positioning unit is used to determine the first position through the positioning module when the electric field data is greater than a preset electric field data threshold and / or the magnetic field data is greater than a preset magnetic field data threshold.
[0095] Optionally, the image acquisition module 303 includes:
[0096] The walking distance determination unit is used to determine the walking distance based on the first position and the calibration parameters of the camera;
[0097] An image acquisition unit is used to control the camera to acquire images when the distance between the robot's position and the first position is at least equal to the walking distance.
[0098] Optionally, the insulation sheath anomaly detection model includes an insulation sheath installation anomaly detection sub-model and an insulation sheath fixing anomaly detection sub-model, and the detection result prediction module 304 includes:
[0099] The first prediction unit is used to input the image into the insulation sheath installation anomaly detection sub-model to obtain the insulation sheath installation detection result;
[0100] The second prediction unit is used to input the image into the insulation sheath fixation anomaly detection sub-model to obtain the insulation sheath fixation detection result.
[0101] Optionally, the prompt message sending module 305 includes:
[0102] The prompt information generation unit is used to generate a prompt information about insulation sleeve abnormality using the image and the second position when the insulation sleeve installation detection result is insulation sleeve installation abnormality, and / or the insulation sleeve fixation detection result is insulation sleeve fixation abnormality.
[0103] Optional, also includes:
[0104] An insulation performance abnormality warning information sending unit is used to generate an insulation performance abnormality warning information using the electromagnetic data when the electromagnetic data exceeds a preset threshold, and to send the insulation performance abnormality warning information to the system backend.
[0105] The insulation sheath inspection device provided in this embodiment of the invention can execute the insulation sheath inspection method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.
[0106] Example 4
[0107] Figure 4 A schematic diagram of the structure of an inspection robot 40 that can be used to implement an embodiment of the present invention is shown. Figure 4 As shown, the inspection robot 40 includes a camera 46, an electromagnetic measuring device 47, at least one processor 41, and a memory. The camera 46, the electromagnetic measuring device 47, and the memory are all connected to the at least one processor. The memory includes, for example, a read-only memory (ROM) 42 and a random access memory (RAM) 43. The memory stores computer programs executable by the at least one processor. The processor 41 can perform various appropriate actions and processes based on the computer programs stored in the ROM 42 or loaded from the storage unit 48 into the RAM 43. The RAM 43 can also store various programs and data required for the operation of the inspection robot 40. The processor 41, ROM 42, and RAM 43 are interconnected via a bus 44, and an input / output (I / O) interface 45 is also connected to the bus 44.
[0108] The camera 46, electromagnetic measuring device 47, storage unit 48, and communication unit 49 in the inspection robot 40 are connected to the I / O interface 45. The storage unit 48 is, for example, a hard disk or optical disk; the communication unit 49 is, for example, a network card, modem, or wireless transceiver. The communication unit 49 allows the inspection robot 40 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0109] Processor 41 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 41 performs the various methods and processes described above, such as the insulation sheath inspection method.
[0110] In some embodiments, the insulation sheath inspection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 48. In some embodiments, part or all of the computer program may be loaded and / or installed on the inspection robot 40 via ROM 42 and / or communication unit 49. When the computer program is loaded into RAM 43 and executed by processor 41, one or more steps of the insulation sheath inspection method described above may be performed. Alternatively, in other embodiments, processor 41 may be configured to perform the insulation sheath inspection method by any other suitable means (e.g., by means of firmware).
[0111] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.
[0112] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0113] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.
[0114] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.
[0115] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.
Claims
1. A method for inspecting insulating sheaths, characterized in that, Inspection robots equipped with cameras, electromagnetic measuring devices, and positioning modules include: During the process of controlling the robot to walk on the power transmission line, electromagnetic data is collected through an electromagnetic measuring device. When the electromagnetic data is greater than a preset threshold, the positioning module determines a first position, which is the position where electromagnetic data greater than the preset threshold is collected. The robot is controlled to walk and collect an image at the first position on the power transmission line, and a second position is determined by the positioning module, the second position being the position when the image at the first position was collected; The image is input into the insulation sheath anomaly detection model to obtain the detection result; When the detection result indicates an abnormality in the insulation sheath, a notification message indicating an abnormality in the insulation sheath is sent to the system backend. The insulation sheath anomaly detection model includes an insulation sheath installation anomaly detection sub-model and an insulation sheath fixation anomaly detection sub-model. The step of inputting the image into the insulation sheath anomaly detection model to obtain the detection result includes: The image is input into the insulation sheath installation anomaly detection sub-model to obtain the insulation sheath installation detection result; The image is input into the insulation sheath fixation anomaly detection sub-model to obtain the insulation sheath fixation detection result.
2. The method for inspecting insulating sheaths as described in claim 1, characterized in that, As the controlled robot moves along the power transmission line, it collects electromagnetic data through an electromagnetic measurement device, including: While controlling the robot to walk on the power transmission line, electric field and magnetic field data are collected through electromagnetic measuring devices.
3. The method for inspecting insulating sheaths as described in claim 2, characterized in that, When the electromagnetic data exceeds a preset threshold, the positioning module determines a first position, including: When the electric field data is greater than a preset electric field data threshold, and / or the magnetic field data is greater than a preset magnetic field data threshold, the positioning module determines the first position.
4. The method for inspecting insulating sheaths as described in claim 2, characterized in that, The process of controlling the robot to walk and acquiring an image at the first location on the power transmission line includes: The walking distance is determined based on the first location and the calibration parameters of the camera; When the distance between the robot's position and the first position is at least equal to the walking distance, the camera is controlled to capture images.
5. The method for inspecting insulating sheaths as described in claim 1, characterized in that, When the detection result indicates an abnormality in the insulation sheath, a notification message indicating an abnormality in the insulation sheath is sent to the system backend, including: When the insulation sleeve installation test result is an insulation sleeve installation abnormality, and / or the insulation sleeve fixation test result is an insulation sleeve fixation abnormality, the image and the second position are used to generate an insulation sleeve abnormality prompt message.
6. The method for inspecting insulating sheaths as described in any one of claims 1-4, characterized in that, Also includes: When the electromagnetic data exceeds a preset threshold, an insulation performance abnormality warning message is generated using the electromagnetic data and sent to the system backend.
7. An inspection device for insulating sheaths, characterized in that, Inspection robots equipped with cameras, electromagnetic measuring devices, and positioning modules include: The electromagnetic data acquisition module is used to collect electromagnetic data through an electromagnetic measuring device while controlling the robot to walk on the power transmission line. The first positioning module is used to determine a first position when the electromagnetic data is greater than a preset threshold, wherein the first position is the position where electromagnetic data greater than the threshold is collected; The image acquisition module is used to control the robot to walk and acquire an image at the first position on the power transmission line, and to determine a second position through the positioning module, wherein the second position is the position when the image at the first position was acquired; The detection result prediction module is used to input the image into the insulation sheath anomaly detection model to obtain the detection result; The prompt message sending module is used to send a prompt message indicating that the insulation sheath is abnormal to the system backend when the detection result indicates that the insulation sheath is abnormal. The insulation sheath anomaly detection model includes an insulation sheath installation anomaly detection sub-model and an insulation sheath fixing anomaly detection sub-model. The detection result prediction module includes: The first prediction unit is used to input the image into the insulation sheath installation anomaly detection sub-model to obtain the insulation sheath installation detection result; The second prediction unit is used to input the image into the insulation sheath fixation anomaly detection sub-model to obtain the insulation sheath fixation detection result.
8. An inspection robot, characterized in that, The inspection robot includes: The system includes a camera, a positioning module, an electromagnetic measuring device, at least one processor, and a memory. The camera, positioning module, electromagnetic measuring device, and memory are all connected to the at least one processor. The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the insulation sheath inspection method according to any one of claims 1-6.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the insulation sheath inspection method according to any one of claims 1-6.
Citation Information
Patent Citations
Method for detection of high voltage cable based on robot and robot
CN106802374A
Abnormality detection method and device, electronic equipment and storage medium
CN113726606A
