CN112906620A - Unmanned aerial vehicle-assisted insulator fault detection method and device and electronic equipment - Google Patents
Unmanned aerial vehicle-assisted insulator fault detection method and device and electronic equipment Download PDFInfo
- Publication number
- CN112906620A CN112906620A CN202110258375.8A CN202110258375A CN112906620A CN 112906620 A CN112906620 A CN 112906620A CN 202110258375 A CN202110258375 A CN 202110258375A CN 112906620 A CN112906620 A CN 112906620A
- Authority
- CN
- China
- Prior art keywords
- insulator
- fault
- fault detection
- detection
- detected
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
Abstract
The invention provides an unmanned aerial vehicle-assisted insulator fault detection method, an unmanned aerial vehicle-assisted insulator fault detection device and electronic equipment, wherein the method comprises the following steps: acquiring a detection image acquired when an unmanned aerial vehicle flies to an insulator to be detected; extracting a target image of the insulator to be detected from the detection image based on a target segmentation model, wherein the target segmentation model is obtained based on a sample detection image and an insulator region label training thereof; and carrying out fault detection on the target image based on a fault detection model to obtain a fault detection result of the insulator to be detected, wherein the fault detection model is obtained based on sample insulator images and fault labels thereof. The method, the device and the electronic equipment provided by the embodiment of the invention realize special detection of the insulator component with multiple faults, simultaneously avoid the interference of noise information such as background environment and the like, and improve the detection precision of the insulator fault.
Description
Technical Field
The invention relates to the technical field of fault detection, in particular to an unmanned aerial vehicle-assisted insulator fault detection method and device and electronic equipment.
Background
With the increasing expansion of the scale of the power grid in China, the guarantee of safe, reliable and stable operation of the power grid becomes an important content for the construction of the smart power grid. The insulator is an extremely important and abundant part in the power grid, plays a role in electrical insulation and mechanical support, is exposed outdoors for a long time and is tested in various environments and climates, and surface defects such as surface dirt, cracks, breakage and the like seriously threaten the safe operation of the power grid. It is statistical that accidents caused by insulator defects have become the highest percentage of power system failures. Therefore, the intelligent detection is carried out on the surface defects of the insulator, the fault prejudgment and diagnosis are completed in time, and the intelligent detection method has important practical significance.
In recent years, with the rapid development of unmanned aerial vehicle technology, the unmanned aerial vehicle-assisted power transmission line inspection mode is gradually applied. In the current stage, a common inspection mode is to collect an image of a target line, transmit the image to a fault identification model, and judge the fault probability and the corresponding fault type through the fault identification model. However, the above-described technique has the following problems: insulator components with frequent faults are not specially detected; after the collected images are transmitted to the fault recognition model, fault recognition is directly carried out, and due to the fact that the shooting distance of the unmanned aerial vehicle is long, most of information contained in the original images is useless information such as environment, and recognition accuracy can be seriously affected.
Disclosure of Invention
The invention provides an unmanned aerial vehicle-assisted insulator fault detection method, an unmanned aerial vehicle-assisted insulator fault detection device and electronic equipment, which are used for solving the defects that the special detection on an insulator part is lacked and the identification precision is poor in the prior art, realizing the special detection on the insulator part, avoiding the interference of noise information such as background environment and the like and improving the detection precision of insulator faults.
The invention provides an unmanned aerial vehicle-assisted insulator fault detection method, which comprises the following steps:
acquiring a detection image acquired when an unmanned aerial vehicle flies to an insulator to be detected;
extracting a target image of the insulator to be detected from the detection image based on a target segmentation model, wherein the target segmentation model is obtained based on a sample detection image and an insulator region label training thereof;
and carrying out fault detection on the target image based on a fault detection model to obtain a fault detection result of the insulator to be detected, wherein the fault detection model is obtained based on sample insulator images and fault labels thereof.
According to the insulator fault detection method assisted by the unmanned aerial vehicle, the method for acquiring the detection image acquired by the unmanned aerial vehicle flying to the insulator to be detected comprises the following steps:
and controlling the unmanned aerial vehicle to fly based on an inspection track, wherein the inspection track is obtained by performing path planning by taking the minimum flying distance as a target based on the flying starting and ending point position and the positions of all insulators to be detected.
According to the unmanned aerial vehicle-assisted insulator fault detection method provided by the invention, the inspection track is determined based on the following steps:
taking the flight starting and ending point position and the positions of all insulators to be detected as nodes, and constructing a node set;
taking the distance between every two nodes in the node set as the edge weight between every two nodes to construct an edge set;
and performing shortest path planning based on the node set and the edge set to obtain the routing inspection track.
According to the unmanned aerial vehicle-assisted insulator fault detection method provided by the invention, the target image of the insulator to be detected is extracted from the detection image based on the target segmentation model, and the method comprises the following steps:
and based on the target segmentation model, carrying out insulator target identification and segmentation on the detection image to obtain a target image of the insulator to be detected.
According to the unmanned aerial vehicle-assisted insulator fault detection method provided by the invention, the fault detection module carries out fault detection on the target image to obtain a fault detection result of the insulator to be detected, and the fault detection method comprises the following steps:
based on a detection layer of a fault detection model, respectively carrying out damage deformation detection, surface pollution detection and flashover burn detection on the target image to obtain a damage deformation probability, a surface pollution probability and a flashover burn probability;
and obtaining the fault detection result by applying the damage deformation probability, the surface pollution probability and the flashover burn probability based on an output layer of the fault detection model.
According to the unmanned aerial vehicle-assisted insulator fault detection method provided by the invention, the fault detection result is a fault early warning score;
the obtaining of the fault detection result of the insulator to be detected further includes:
and if the fault early warning score is larger than a preset fault threshold value, carrying out fault early warning.
According to the unmanned aerial vehicle-assisted insulator fault detection method provided by the invention, the fault early warning is carried out, and the method comprises the following steps:
and sending fault early warning information to a monitoring system, wherein the fault early warning information comprises the position of the insulator to be detected or comprises the position of the insulator to be detected and a detection image corresponding to the position of the insulator to be detected. The invention also provides an unmanned aerial vehicle-assisted insulator fault detection device, which comprises:
the acquisition module is used for acquiring a detection image acquired when the unmanned aerial vehicle flies to the insulator to be detected;
the target segmentation module is used for extracting a target image of the insulator to be detected from the detection image based on a target segmentation model, and the target segmentation model is obtained based on a sample detection image and an insulator region label training thereof;
and the fault detection module is used for carrying out fault detection on the target image based on a fault detection model to obtain a fault detection result of the insulator to be detected, and the fault detection model is obtained based on sample insulator images and fault labels thereof.
The invention also provides electronic equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the program to realize the steps of the unmanned aerial vehicle-assisted insulator fault detection method.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the drone assisted insulator fault detection method according to any of the above.
According to the unmanned aerial vehicle-assisted insulator fault detection method, the unmanned aerial vehicle-assisted insulator fault detection device and the electronic equipment, the special detection of the insulator component with frequent faults is realized by acquiring the detection image acquired by the unmanned aerial vehicle flying to the insulator to be detected; the target segmentation model is adopted to extract the target image of the insulator to be detected from the detection image, so that the interference of noise information such as background environment and the like is avoided, and the robustness of the acquired image quality of the insulator to be detected is improved; the fault detection model is adopted to carry out fault detection on the target image to obtain a fault detection result, so that the detection precision of the insulator fault is improved, the problem that the insulator fault is difficult to prejudge in the prior art is solved, and the method has good application prospect and popularization value.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is one of schematic flow diagrams of an unmanned aerial vehicle-assisted insulator fault detection method according to an embodiment of the present invention;
fig. 2 is a second schematic flowchart of an unmanned aerial vehicle-assisted insulator fault detection method according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an unmanned aerial vehicle-assisted insulator fault detection apparatus provided in an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
At present, accidents caused by insulator defects are the most important faults in power systems. And current supplementary transmission line of unmanned aerial vehicle patrols and examines the mode and does not carry out special detection to the insulator part that the trouble is many to, because unmanned aerial vehicle shoots the distance far away, contain most information garbage information in the image of gathering, prior art directly transmits original image to the trouble recognition model and discerns, has the relatively poor problem of discernment precision. In order to solve the problems, the embodiments of the invention fully consider the practical application scene of the fault detection of the auxiliary insulator of the unmanned aerial vehicle, and discloses an auxiliary insulator fault detection method of the unmanned aerial vehicle, which realizes the special detection of the insulator components with multiple faults, avoids the interference of noise information such as background environment and the like, and improves the detection precision of the insulator faults.
The execution main body of the insulator fault detection method assisted by the unmanned aerial vehicle can be a processor carried on the unmanned aerial vehicle or a processor of a system background. Considering that the method is not large in calculation energy consumption, the calculation capacity of a processor carried on the unmanned aerial vehicle can meet requirements, and if the image or video acquired by the unmanned aerial vehicle is directly transmitted to a system background for processing, large transmission power consumption is caused, so that the processor carried on the unmanned aerial vehicle is preferably used as an execution main body of the insulator fault detection method. Fig. 1 is a schematic flow diagram of an unmanned aerial vehicle-assisted insulator fault detection method provided by the present invention, and as shown in fig. 1, the method includes:
step 100, acquiring a detection image acquired when the unmanned aerial vehicle flies to the insulator to be detected.
Specifically, when unmanned aerial vehicle flies and arrives near every insulator that waits to detect, unmanned aerial vehicle launches the camera of carrying on and detects the collection of image, and on this basis, the treater can acquire the detection image from the camera, carries out subsequent fault detection. Here, the detection image may be any image that needs to be subjected to insulator fault detection, for example, an image captured by a camera, or a video frame extracted from a video captured by a camera, which is not particularly limited in the embodiment of the present invention.
And 110, extracting a target image of the insulator to be detected from the detection image based on a target segmentation model, wherein the target segmentation model is obtained based on the sample detection image and the insulator region label training thereof.
Specifically, considering that due to the limitation of the shooting distance, most of the acquired detection images are noise information interfering with the judgment of the state of the insulator, such as the background environment, the embodiment of the invention adopts a target segmentation model to segment the insulator region from the background region in the acquired detection images, and extracts the image of the insulator region of interest as the target image.
The target segmentation model may be a U-Net network model, a SegNet network model, an E-Net network model, or another neural network model capable of achieving the target segmentation function, and the embodiment of the present invention does not specifically limit the type and structure of the target segmentation model.
Before the steps are executed, a target segmentation model can be obtained through pre-training, and the obtained target segmentation model is deployed on the unmanned aerial vehicle. The target segmentation model can be obtained by the following training mode: firstly, a large number of sample detection images are collected, and for each sample detection image, the boundary of an insulator region in the sample detection image is marked to obtain an insulator region label of the sample detection image. And then, training the initial target segmentation model based on the sample detection image and the insulator region label of the sample detection image, thereby obtaining the target segmentation model.
And 120, carrying out fault detection on the target image based on the fault detection model to obtain a fault detection result of the insulator to be detected, wherein the fault detection model is obtained based on sample insulator images and fault labels thereof.
Specifically, after the target image is obtained, the target image is input into a fault detection model for fault detection, and a fault detection result of the insulator to be detected is output. The fault detection model can be a convolutional neural network model, a capsule network model or other neural network models capable of realizing fault detection, and the embodiment of the invention does not specifically limit the type and structure of the fault detection model.
Before the steps are executed, a fault detection model can be obtained through pre-training, and the obtained fault detection model is deployed on the unmanned aerial vehicle. The fault detection model can be obtained by the following training mode: firstly, collecting a large number of sample insulator images, and marking the fault state of each sample insulator image to obtain the fault label of the sample insulator image, wherein the fault label comprises whether the sample insulator has damage deformation, whether surface dirt exists, whether flashover burn exists and the like. And then training the initial fault detection model based on the sample insulator image and the fault label of the sample insulator image so as to obtain the fault detection model.
According to the method provided by the embodiment of the invention, the special detection of the insulator component with frequent faults is realized by acquiring the detection image acquired by the unmanned aerial vehicle flying to the insulator to be detected; the target segmentation model is adopted to extract the target image of the insulator to be detected from the detection image, so that the interference of noise information such as background environment and the like is avoided, and the robustness of the acquired image quality of the insulator to be detected is improved; the fault detection model is adopted to carry out fault detection on the target image to obtain a fault detection result, so that the detection precision of the insulator fault is improved, the problem that the insulator fault is difficult to prejudge in the prior art is solved, and the method has good application prospect and popularization value.
Based on any of the above embodiments, step 100 further includes:
and controlling the unmanned aerial vehicle to fly based on the inspection track, wherein the inspection track is obtained by planning a path by taking the minimum flying distance as a target based on the flying starting and ending point position and the positions of all insulators to be detected.
Specifically, considering that the energy of the unmanned aerial vehicle is limited, in order to reduce unnecessary energy consumption in the routing inspection process of the unmanned aerial vehicle, the embodiment of the invention optimizes the flight trajectory of the unmanned aerial vehicle from the flight starting point to the flight end point after traversing all the insulators to be detected, and performs path planning by taking the minimum flight distance as a target according to the flight starting point position, the flight end point position and the positions of all the insulators to be detected of the unmanned aerial vehicle, so that the routing inspection trajectory can be finally determined, and the total distance of the unmanned aerial vehicle flying after completing the routing inspection work is shortest. On this basis, can control unmanned aerial vehicle and fly according to the orbit of patrolling and examining that plans, accomplish the collection task of the detection image of waiting to detect the insulator.
According to the method provided by the embodiment of the invention, the minimum flight distance is taken as a target to perform path planning to obtain the routing inspection track based on the flight starting and ending point position and the positions of all insulators to be detected, so that the total distance of the unmanned aerial vehicle after finishing the routing inspection work is shortest, the energy efficiency of the unmanned aerial vehicle is improved to the greatest extent, and the problem of track optimization in the prior art that the unmanned aerial vehicle executes a routing inspection task is not considered is solved.
Based on any one of the embodiments, the routing inspection track is determined based on the following steps:
taking the flight starting and ending point position and the positions of all insulators to be detected as nodes, and constructing a node set;
taking the distance between every two nodes in the node set as the edge weight between every two nodes to construct an edge set;
and planning the shortest path based on the node set and the edge set to obtain the routing inspection track.
Specifically, through carrying out the flight track planning of patrolling and examining the in-process to unmanned aerial vehicle, can obtain and patrol and examine the orbit, concrete step is as follows:
firstly, the flight starting point position, the flight end point position and the positions of all insulators to be detected of the unmanned aerial vehicle are used as nodes, and therefore a node set V is constructed. Then, the distance between every two nodes in the node set V is used as the edge weight between every two nodes, all the edge weights are combined into an edge set E, on the basis, the unmanned aerial vehicle track planning problem can be modeled into a shortest path planning problem with a weighted directed graph G (V, E), and then the shortest path planning problem is solved by adopting a track planning algorithm, so that the routing inspection track is obtained. Here, the trajectory planning algorithm may be Dijkstra algorithm, Floyd algorithm, or other algorithms capable of solving the shortest path planning problem.
Based on any of the above embodiments, in step 110, extracting a target image of an insulator to be detected from a detection image based on a target segmentation model, includes:
and based on the target segmentation model, carrying out insulator target identification and segmentation on the detection image to obtain a target image of the insulator to be detected.
Specifically, after a detection image acquired by the unmanned aerial vehicle is acquired, a target segmentation model is adopted to perform target identification and segmentation on the detection image in an insulator region, so as to obtain a target image of the insulator to be detected, and the method can be specifically realized through the following steps: firstly, inputting a detection image into a target segmentation model, outputting a mask image with insulator region boundary information, and multiplying the mask image and the detection image to keep the pixel values of pixels in the insulator region boundary in the detection image unchanged, and the pixel values of pixels outside the boundary are all 0, namely, the background region is processed to be completely black. Then, the processed detection image can be cut under the premise of ensuring the integrity of the insulator region, that is, the image of the insulator region is cut from the processed detection image according to the difference of the pixel values and is used as a target image.
According to the method provided by the embodiment of the invention, the target segmentation model is adopted to identify and segment the insulator target of the detection image, so that the target image of the insulator to be detected is obtained, the subsequent fault detection of the insulator to be detected is facilitated, the interference of noise information such as background environment and the like on the fault identification precision is avoided, and the robustness of the acquired image quality of the insulator to be detected is improved.
Based on any of the above embodiments, in step 120, performing fault detection on the target image based on the fault detection model to obtain a fault detection result of the insulator to be detected, including:
based on a detection layer of a fault detection model, respectively carrying out damage deformation detection, surface pollution detection and flashover burn detection on a target image to obtain a damage deformation probability, a surface pollution probability and a flashover burn probability;
and obtaining a fault detection result by applying the damage deformation probability, the surface pollution probability and the flashover burn probability based on an output layer of the fault detection model.
Specifically, considering that there may be multiple fault types in the insulator fault, the embodiment of the present invention divides the fault types of the insulator into three aspects of damage deformation (crack, glaze shortage, expansion, defect, etc.), surface contamination, and flashover burn, and comprehensively evaluates the fault state of the insulator from the three aspects:
firstly, inputting a target image into a fault detection model; then, based on the detection layer of the fault detection model, the target image can be subjected to damage deformation detection, surface pollution detection and flashover burn detection respectively to obtain the damage deformation probability r1Surface contamination probability r2And flashover burn probability r3(ii) a Finally, based on the output layer of the fault detection model, the damage deformation probability r can be applied1Surface contamination probability r2And flashover burn probability r3And obtaining a fault detection result of the insulator to be detected. Here, the application mode of the output layer is not specifically limited in the embodiment of the present invention, and for example, r may be r1、r2、r3The three probabilities are added to obtain a fault detection result, or the three probabilities are weighted to obtain a fault detection result, or r is weighted to obtain a fault detection result1、r2、r3And comparing the fault with a corresponding threshold value to obtain a fault detection result.
Based on any of the above embodiments, the fault detection result is a fault early warning score;
in step 120, obtaining a fault detection result of the insulator to be detected, and then:
and if the fault early warning score is larger than a preset fault threshold value, carrying out fault early warning.
Specifically, the fault early warning score of the insulator to be detected can reflect the probability that the fault exists in the insulator to be detected, and the higher the early warning score is, the higher the probability that the fault occurs in the insulator to be detected is. After the fault early warning score is obtained, the value of the fault early warning score can be judged:
if the fault early warning score is larger than the preset fault threshold value, the fault early warning is started to inform electric power personnel to timely process the insulator with the fault, and the safety accident of the power grid is avoided;
otherwise, the fault early warning score is smaller than or equal to the preset fault threshold value, which indicates that the insulator to be detected has no fault or the fault degree of the insulator to be detected is relatively light, and the insulator does not need to be processed.
Here, the preset failure threshold may be set arbitrarily according to a user requirement, which is not specifically limited in the embodiment of the present invention.
Based on any one of the above embodiments, performing fault early warning includes:
and sending fault early warning information to a monitoring system, wherein the fault early warning information comprises the position of the insulator to be detected or the position of the insulator to be detected and a detection image corresponding to the position.
Specifically, when the insulator to be detected breaks down, the fault early warning is started, the fault early warning information can be sent to the monitoring system, and then the monitoring system issues the early warning information according to the received fault early warning information. Here, the fault warning information including the position of the insulator to be detected, which is determined to have a fault, may be sent to the monitoring system, so that the power personnel may process the insulator having the fault according to the position. Optionally, the detection image of the insulator to be detected with the determined fault can be sent to the monitoring system, so that the monitoring system can display the detection image of the insulator with the fault, and the detection image is convenient for electric power personnel to check.
Based on any embodiment, the target segmentation model is constructed based on U-Net, and the fault detection model is constructed based on a capsule network.
Specifically, the target segmentation model for extracting the target image of the insulator to be detected from the detected image can be constructed based on a U-Net network model, and the U-Net network model is a deep learning model with good image segmentation performance, so that the accurate segmentation of the image of the insulator region can be realized, and the robustness of the acquired image quality of the insulator to be detected is improved.
In view of the problem that images acquired by an unmanned aerial vehicle have different shooting angles or fuzzy ghosts due to the fact that the unmanned aerial vehicle flies, the embodiment of the invention adopts a capsule network to construct a fault detection model for performing fault detection on a target image to obtain a fault detection result. The capsule network is a novel neural network structure provided by Geofrey Hinton, can accurately analyze the state of the insulator and carry out fault prejudgment in images with changed shooting angles and fuzzy shooting ghosts, and solves the problem that the image identification effect is poor in the prior art.
Based on any of the above embodiments, fig. 2 is a schematic flow chart of the unmanned aerial vehicle-assisted insulator fault detection method provided by the embodiment of the present invention, and as shown in fig. 2, positions of all insulators to be detected need to be determined first, and then, according to a flight starting point position, a flight end point position of the unmanned aerial vehicle and positions of all insulators to be detected, a trajectory planning algorithm is adopted to perform trajectory optimization on the unmanned aerial vehicle, so as to obtain a routing inspection trajectory with the shortest total flight distance. On this basis, control unmanned aerial vehicle flies according to patrolling and examining the orbit, and when unmanned aerial vehicle arrived near every position of waiting to detect the insulator, unmanned aerial vehicle started the camera and carries out the collection that detects the image. After the processor on the unmanned aerial vehicle acquires the detection image, the fault prejudgment of the insulator to be detected can be carried out:
firstly, extracting a target image of an insulator to be detected from a detection image by adopting a U-Net network model;
secondly, fault detection is carried out on the target image by adopting a capsule network model to obtain a fault detection result of the insulator to be detected;
and finally, judging whether the fault detection result, namely the fault early warning score is larger than a preset fault threshold value or not, if so, starting fault early warning, sending fault early warning information to a monitoring system, and then issuing early warning information by the monitoring system according to the received fault early warning information.
It should be noted that the unmanned aerial vehicle used in the embodiment of the present invention needs to be equipped with image acquisition, calculation, communication, and positioning functions.
Based on any of the above method embodiments, fig. 3 is a schematic structural diagram of an unmanned aerial vehicle-assisted insulator fault detection apparatus provided in an embodiment of the present invention, and as shown in fig. 3, the apparatus includes:
the acquisition module 300 is used for acquiring a detection image acquired by the unmanned aerial vehicle flying to the insulator to be detected;
the target segmentation module 310 is configured to extract a target image of an insulator to be detected from the detection image based on a target segmentation model, where the target segmentation model is obtained based on a sample detection image and an insulator region label training thereof;
and the fault detection module 320 is configured to perform fault detection on the target image based on a fault detection model to obtain a fault detection result of the insulator to be detected, wherein the fault detection model is obtained based on a sample insulator image and a fault label training thereof.
It should be noted that, the obtaining module 300, the target segmenting module 310, and the fault detecting module 320 cooperate to execute the method for detecting the insulator fault assisted by the unmanned aerial vehicle in the above embodiment, and specific functions of the system refer to the above embodiment of the method for detecting the insulator fault assisted by the unmanned aerial vehicle, which is not described herein again.
According to the device provided by the embodiment of the invention, the special detection of the insulator component with multiple faults is realized by acquiring the detection image acquired by the unmanned aerial vehicle flying to the insulator to be detected; the target segmentation model is adopted to extract the target image of the insulator to be detected from the detection image, so that the interference of noise information such as background environment and the like is avoided, and the robustness of the acquired image quality of the insulator to be detected is improved; the fault detection model is adopted to carry out fault detection on the target image to obtain a fault detection result, so that the detection precision of the insulator fault is improved, the problem that the insulator fault is difficult to prejudge in the prior art is solved, and the method has good application prospect and popularization value.
Based on any embodiment, the apparatus further comprises a flight control module configured to:
and controlling the unmanned aerial vehicle to fly based on the inspection track, wherein the inspection track is obtained by planning a path by taking the minimum flying distance as a target based on the flying starting and ending point position and the positions of all insulators to be detected.
Based on any of the above embodiments, the apparatus further comprises a trajectory planning module, configured to:
taking the flight starting and ending point position and the positions of all insulators to be detected as nodes, and constructing a node set;
taking the distance between every two nodes in the node set as the edge weight between every two nodes to construct an edge set;
and planning the shortest path based on the node set and the edge set to obtain the routing inspection track.
Based on any of the above embodiments, the target segmentation module 310 is specifically configured to:
and based on the target segmentation model, carrying out insulator target identification and segmentation on the detection image to obtain a target image of the insulator to be detected.
Based on any of the embodiments above, the fault detection module 320 is specifically configured to:
based on a detection layer of a fault detection model, respectively carrying out damage deformation detection, surface pollution detection and flashover burn detection on a target image to obtain a damage deformation probability, a surface pollution probability and a flashover burn probability;
and obtaining a fault detection result by applying the damage deformation probability, the surface pollution probability and the flashover burn probability based on an output layer of the fault detection model.
Based on any of the above embodiments, the fault detection result is a fault early warning score;
the device also comprises a fault early warning module used for:
and if the fault early warning score is larger than a preset fault threshold value, carrying out fault early warning.
Based on any of the above embodiments, the fault early warning module is specifically configured to:
and sending fault early warning information to a monitoring system, wherein the fault early warning information comprises the position of the insulator to be detected or the position of the insulator to be detected and a detection image corresponding to the position.
Fig. 4 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 4: a processor (processor)410, a communication Interface 420, a memory (memory)430 and a communication bus 440, wherein the processor 410, the communication Interface 420 and the memory 430 are communicated with each other via the communication bus 440. Processor 410 may invoke logic instructions in memory 430 to perform a drone assisted insulator fault detection method comprising: acquiring a detection image acquired when an unmanned aerial vehicle flies to an insulator to be detected; extracting a target image of the insulator to be detected from the detection image based on a target segmentation model, wherein the target segmentation model is obtained based on a sample detection image and an insulator region label training thereof; and performing fault detection on the target image based on a fault detection model to obtain a fault detection result of the insulator to be detected, wherein the fault detection model is obtained based on sample insulator images and fault labels thereof.
In addition, the logic instructions in the memory 430 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the drone assisted insulator fault detection method provided by the above methods, the method comprising: acquiring a detection image acquired when an unmanned aerial vehicle flies to an insulator to be detected; extracting a target image of the insulator to be detected from the detection image based on a target segmentation model, wherein the target segmentation model is obtained based on a sample detection image and an insulator region label training thereof; and performing fault detection on the target image based on a fault detection model to obtain a fault detection result of the insulator to be detected, wherein the fault detection model is obtained based on sample insulator images and fault labels thereof.
In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium having stored thereon a computer program, which when executed by a processor, is implemented to perform the above-mentioned drone-assisted insulator fault detection methods, the method comprising: acquiring a detection image acquired when an unmanned aerial vehicle flies to an insulator to be detected; extracting a target image of the insulator to be detected from the detection image based on a target segmentation model, wherein the target segmentation model is obtained based on a sample detection image and an insulator region label training thereof; and performing fault detection on the target image based on a fault detection model to obtain a fault detection result of the insulator to be detected, wherein the fault detection model is obtained based on sample insulator images and fault labels thereof.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. An unmanned aerial vehicle-assisted insulator fault detection method is characterized by comprising the following steps:
acquiring a detection image acquired when an unmanned aerial vehicle flies to an insulator to be detected;
extracting a target image of the insulator to be detected from the detection image based on a target segmentation model, wherein the target segmentation model is obtained based on a sample detection image and an insulator region label training thereof;
and carrying out fault detection on the target image based on a fault detection model to obtain a fault detection result of the insulator to be detected, wherein the fault detection model is obtained based on sample insulator images and fault labels thereof.
2. The method for detecting insulator faults assisted by an unmanned aerial vehicle according to claim 1, wherein the acquiring of the detection image acquired when the unmanned aerial vehicle flies to the insulator to be detected further comprises:
and controlling the unmanned aerial vehicle to fly based on an inspection track, wherein the inspection track is obtained by performing path planning by taking the minimum flying distance as a target based on the flying starting and ending point position and the positions of all insulators to be detected.
3. The unmanned aerial vehicle-assisted insulator fault detection method of claim 2, wherein the routing inspection trajectory is determined based on the following steps:
taking the flight starting and ending point position and the positions of all insulators to be detected as nodes, and constructing a node set;
taking the distance between every two nodes in the node set as the edge weight between every two nodes to construct an edge set;
and performing shortest path planning based on the node set and the edge set to obtain the routing inspection track.
4. The unmanned aerial vehicle-assisted insulator fault detection method according to claim 1, wherein the extracting a target image of the insulator to be detected from the detection image based on a target segmentation model comprises:
and based on the target segmentation model, carrying out insulator target identification and segmentation on the detection image to obtain a target image of the insulator to be detected.
5. The unmanned aerial vehicle-assisted insulator fault detection method of claim 1, wherein the fault detection of the target image based on the fault detection model to obtain the fault detection result of the insulator to be detected comprises:
based on a detection layer of a fault detection model, respectively carrying out damage deformation detection, surface pollution detection and flashover burn detection on the target image to obtain a damage deformation probability, a surface pollution probability and a flashover burn probability;
and obtaining the fault detection result by applying the damage deformation probability, the surface pollution probability and the flashover burn probability based on an output layer of the fault detection model.
6. The unmanned aerial vehicle-assisted insulator fault detection method according to any one of claims 1 to 5, wherein the fault detection result is a fault early warning score;
the obtaining of the fault detection result of the insulator to be detected further includes:
and if the fault early warning score is larger than a preset fault threshold value, carrying out fault early warning.
7. The unmanned aerial vehicle-assisted insulator fault detection method of claim 6, wherein the performing fault early warning comprises:
and sending fault early warning information to a monitoring system, wherein the fault early warning information comprises the position of the insulator to be detected or comprises the position of the insulator to be detected and a detection image corresponding to the position of the insulator to be detected.
8. The utility model provides an unmanned aerial vehicle assisted insulator fault detection device which characterized in that includes:
the acquisition module is used for acquiring a detection image acquired when the unmanned aerial vehicle flies to the insulator to be detected;
the target segmentation module is used for extracting a target image of the insulator to be detected from the detection image based on a target segmentation model, and the target segmentation model is obtained based on a sample detection image and an insulator region label training thereof;
and the fault detection module is used for carrying out fault detection on the target image based on a fault detection model to obtain a fault detection result of the insulator to be detected, and the fault detection model is obtained based on sample insulator images and fault labels thereof.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of the drone assisted insulator fault detection method according to any one of claims 1 to 7.
10. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the steps of the drone-assisted insulator fault detection method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110258375.8A CN112906620B (en) | 2021-03-09 | 2021-03-09 | Unmanned aerial vehicle-assisted insulator fault detection method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110258375.8A CN112906620B (en) | 2021-03-09 | 2021-03-09 | Unmanned aerial vehicle-assisted insulator fault detection method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112906620A true CN112906620A (en) | 2021-06-04 |
| CN112906620B CN112906620B (en) | 2022-10-28 |
Family
ID=76107057
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110258375.8A Active CN112906620B (en) | 2021-03-09 | 2021-03-09 | Unmanned aerial vehicle-assisted insulator fault detection method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112906620B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114460918A (en) * | 2021-12-30 | 2022-05-10 | 北京声智科技有限公司 | Equipment detection method, device, equipment and storage medium |
| CN114721419A (en) * | 2022-02-22 | 2022-07-08 | 广州中科云图智能科技有限公司 | Tower inspection method, device and equipment for power transmission line based on unmanned aerial vehicle |
| CN115761537A (en) * | 2022-11-14 | 2023-03-07 | 西安科技大学 | Power transmission line foreign matter intrusion identification method oriented to dynamic characteristic supplement mechanism |
| CN116721095A (en) * | 2023-08-04 | 2023-09-08 | 杭州瑞琦信息技术有限公司 | Aerial photographing road illumination fault detection method and device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106290388A (en) * | 2016-08-03 | 2017-01-04 | 国网山东省电力公司电力科学研究院 | A kind of insulator breakdown automatic testing method |
| CN106525047A (en) * | 2016-10-28 | 2017-03-22 | 重庆交通大学 | Unmanned aerial vehicle path planning method based on floyd algorithm |
| CN107578169A (en) * | 2017-09-04 | 2018-01-12 | 广东电网有限责任公司惠州供电局 | The recognition methods of power network critical circuits and device under the conditions of a kind of typhoon disaster |
| CN108537780A (en) * | 2018-03-27 | 2018-09-14 | 陕西科技大学 | A kind of insulator breakdown detection method based on the full convolutional neural networks of second order |
| CN109118479A (en) * | 2018-07-26 | 2019-01-01 | 中睿能源（北京）有限公司 | Defects of insulator identification positioning device and method based on capsule network |
| CN109801284A (en) * | 2019-01-25 | 2019-05-24 | 华中科技大学 | A kind of high iron catenary insulator breakdown detection method based on deep learning |
| CN111044044A (en) * | 2019-12-06 | 2020-04-21 | 国网安徽省电力有限公司淮南供电公司 | Electric unmanned aerial vehicle routing inspection route planning method and device |
| CN112183667A (en) * | 2020-10-31 | 2021-01-05 | 哈尔滨理工大学 | Insulator fault detection method in cooperation with deep learning |
-
2021
- 2021-03-09 CN CN202110258375.8A patent/CN112906620B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106290388A (en) * | 2016-08-03 | 2017-01-04 | 国网山东省电力公司电力科学研究院 | A kind of insulator breakdown automatic testing method |
| CN106525047A (en) * | 2016-10-28 | 2017-03-22 | 重庆交通大学 | Unmanned aerial vehicle path planning method based on floyd algorithm |
| CN107578169A (en) * | 2017-09-04 | 2018-01-12 | 广东电网有限责任公司惠州供电局 | The recognition methods of power network critical circuits and device under the conditions of a kind of typhoon disaster |
| CN108537780A (en) * | 2018-03-27 | 2018-09-14 | 陕西科技大学 | A kind of insulator breakdown detection method based on the full convolutional neural networks of second order |
| CN109118479A (en) * | 2018-07-26 | 2019-01-01 | 中睿能源（北京）有限公司 | Defects of insulator identification positioning device and method based on capsule network |
| CN109801284A (en) * | 2019-01-25 | 2019-05-24 | 华中科技大学 | A kind of high iron catenary insulator breakdown detection method based on deep learning |
| CN111044044A (en) * | 2019-12-06 | 2020-04-21 | 国网安徽省电力有限公司淮南供电公司 | Electric unmanned aerial vehicle routing inspection route planning method and device |
| CN112183667A (en) * | 2020-10-31 | 2021-01-05 | 哈尔滨理工大学 | Insulator fault detection method in cooperation with deep learning |
Non-Patent Citations (2)
| Title |
|---|
| JINGWEN CHEN ET AL.: "Fault Detection of Insulators Using Second-order Fully Convolutional Network Model", 《MATHEMATICAL PROBLEMS IN ENGINEERING》 * |
| YONGLI WANG ET AL.: "Detection and recognition for fault insulator based on deep learning", 《2018 11TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, BIOMEDICAL ENGINEERING AND INFORMATICS (CISP-BMEI 2018)》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114460918A (en) * | 2021-12-30 | 2022-05-10 | 北京声智科技有限公司 | Equipment detection method, device, equipment and storage medium |
| CN114460918B (en) * | 2021-12-30 | 2024-02-06 | 北京声智科技有限公司 | Method, device, equipment and storage medium for detecting equipment |
| CN114721419A (en) * | 2022-02-22 | 2022-07-08 | 广州中科云图智能科技有限公司 | Tower inspection method, device and equipment for power transmission line based on unmanned aerial vehicle |
| CN114721419B (en) * | 2022-02-22 | 2023-09-19 | 广州中科云图智能科技有限公司 | Tower inspection method, device and equipment based on unmanned aerial vehicle power transmission line |
| CN115761537A (en) * | 2022-11-14 | 2023-03-07 | 西安科技大学 | Power transmission line foreign matter intrusion identification method oriented to dynamic characteristic supplement mechanism |
| CN116721095A (en) * | 2023-08-04 | 2023-09-08 | 杭州瑞琦信息技术有限公司 | Aerial photographing road illumination fault detection method and device |
| CN116721095B (en) * | 2023-08-04 | 2023-11-03 | 杭州瑞琦信息技术有限公司 | Aerial photographing road illumination fault detection method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112906620B (en) | 2022-10-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112906620B (en) | Unmanned aerial vehicle-assisted insulator fault detection method and device and electronic equipment | |
| CN108416294B (en) | Fan blade fault intelligent identification method based on deep learning | |
| CN110703800A (en) | Unmanned aerial vehicle-based intelligent identification method and system for electric power facilities | |
| CN111832398B (en) | Unmanned aerial vehicle image distribution line pole tower ground wire broken strand image detection method | |
| CN113205039B (en) | Power equipment fault image recognition disaster investigation system and method based on multiple DCNN networks | |
| CN112229845A (en) | Unmanned aerial vehicle high-precision winding tower intelligent inspection method based on visual navigation technology | |
| CN113252701B (en) | Cloud edge cooperation-based power transmission line insulator self-explosion defect detection system and method | |
| CN109389322A (en) | The disconnected broken lot recognition methods of grounded-line based on target detection and long memory models in short-term | |
| CN114399484A (en) | Photovoltaic module defect detection method, device, equipment and medium | |
| CN112614130A (en) | Unmanned aerial vehicle power transmission line insulator fault detection method based on 5G transmission and YOLOv3 | |
| CN115169602A (en) | Maintenance method and device for power equipment, storage medium and computer equipment | |
| CN114648708A (en) | State detection method and device of photovoltaic module, storage medium and electronic equipment | |
| CN111060079A (en) | River foreign matter identification method and river foreign matter monitoring platform system | |
| CN115690505A (en) | Photovoltaic module fault detection method and device, computer equipment and storage medium | |
| CN115187880A (en) | Communication optical cable defect detection method and system based on image recognition and storage medium | |
| CN114663375A (en) | Aerostat main cable surface defect detection method and system based on small sample learning | |
| CN115147591A (en) | Transformer equipment infrared image voltage heating type defect diagnosis method and system | |
| CN114445411A (en) | Unmanned aerial vehicle line patrol defect identification system and control method | |
| CN113406107B (en) | Fan blade defect detection system | |
| CN116909320B (en) | Electric power collaborative inspection strategy analysis method based on ant colony algorithm | |
| CN117293697A (en) | Substation floater processing method and device, electronic equipment and storage medium | |
| Zhu et al. | Combining image brightness enhancement algorithm with YOLOv5 for nest detection in power transmission lines | |
| CN108470140B (en) | Power transmission line bird nest identification method based on statistical characteristics and machine learning | |
| CN116030413A (en) | Intrusion detection method, device, equipment and storage medium for parking apron | |
| CN116030127A (en) | Fault positioning method and device for photovoltaic power station and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |