CN114693614A - Defect detection method, device and equipment for vibration damper and storage medium - Google Patents
Defect detection method, device and equipment for vibration damper and storage medium Download PDFInfo
- Publication number
- CN114693614A CN114693614A CN202210259897.4A CN202210259897A CN114693614A CN 114693614 A CN114693614 A CN 114693614A CN 202210259897 A CN202210259897 A CN 202210259897A CN 114693614 A CN114693614 A CN 114693614A
- Authority
- CN
- China
- Prior art keywords
- image
- defect detection
- defect
- vibration damper
- shockproof hammer
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Quality & Reliability (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The invention relates to the technical field of electric power detection, in particular to a method, a device, equipment and a storage medium for detecting a vibration damper defect. According to the method and the device, the area to be detected is determined according to the defect detection instruction of the user, the image acquisition equipment is controlled to acquire the image of the area to be detected according to the defect detection instruction, the acquired image is transmitted back to the terminal equipment, the defect detection is carried out through the preset shockproof hammer defect detection model, and then the position information of the shockproof hammer with the defect is obtained, whether the defect exists or not is not required to be manually identified, the detection efficiency of the shockproof hammer defect is greatly improved, the technical problems that the cost is high and the efficiency is low because the acquired shockproof hammer image is manually judged in the prior art are solved, the efficiency of detecting the shockproof hammer defect is improved, and the cost is saved.
Description
Technical Field
The invention relates to the technical field of electric power detection, in particular to a method, a device, equipment and a storage medium for detecting a vibration damper defect.
Background
At present, the defects of the stockbridge damper and the stockbridge damper of the electric power tower are generally detected by adopting a mode of 'people patrol mainly and machine patrol secondarily', an unmanned aerial vehicle is mainly used for collecting images, and the positions and the number of the defects of the stockbridge damper and the stockbridge damper in the images are manually judged.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide a method, a device, equipment and a storage medium for detecting the defects of a vibration damper, and aims to solve the technical problems that in the prior art, the collected vibration damper image is judged manually, the cost is high and the efficiency is low.
In order to achieve the above object, the present invention provides a method for detecting a defect of a vibration damper, the method comprising the steps of:
when a defect detection instruction is received, determining a region to be detected according to the defect detection instruction;
transmitting the defect detection instruction to image acquisition equipment so that the image acquisition equipment acquires an image to be detected of the area to be detected according to the defect detection instruction and feeds back the image to be detected;
performing defect detection on the image to be detected through a preset vibration damper defect detection model to obtain a vibration damper defect detection result;
and determining the position information of the defective vibration damper according to the detection result of the defect of the vibration damper, and displaying the position information of the defective vibration damper.
Optionally, the detecting the defect of the image to be detected by presetting a vibration damper defect detecting model to obtain a vibration damper defect detecting result includes:
acquiring a storage path and an image name corresponding to the image to be detected;
generating a defect detection message according to the storage path and the image name;
and carrying out defect detection through a preset vibration damper defect detection model according to the defect detection message to obtain a vibration damper defect detection result.
Optionally, the performing defect detection through a preset stockbridge damper defect detection model according to the defect detection message to obtain a stockbridge damper defect detection result includes:
determining a target image according to the defect detection message, and acquiring characteristic information of the target image;
performing defect detection on the target image through a preset stockbridge damper defect detection model based on the characteristic information and a preset search frame to obtain an initial defect detection result;
and acquiring a category confidence coefficient threshold corresponding to the initial defect detection result, and determining a vibration damper defect detection result according to the category confidence coefficient threshold.
Optionally, before the preset stockbridge damper defect detection model is used to perform defect detection on the image to be detected and obtain a stockbridge damper defect detection result, the method further includes:
acquiring a shockproof hammer image sample;
carrying out image annotation on the shockproof hammer image sample according to a preset defect annotation rule to obtain a shockproof hammer annotation image sample;
and carrying out model training on the shockproof hammer image sample and the shockproof hammer labeling image sample through an initial neural network model to obtain a preset shockproof hammer defect detection model.
Optionally, before the image annotation is performed on the shockproof hammer image sample according to a preset defect annotation rule and the shockproof hammer annotation image sample is obtained, the method further includes:
performing overlapping detection on the shockproof hammer image sample to obtain a detection result;
when the detection result is that the shockproof hammer image samples are overlapped, determining a target shockproof hammer and an overlapped shockproof hammer;
acquiring a background color in the shockproof hammer image sample, and updating the overlapped shockproof hammers in the shockproof hammer image sample according to the background color to obtain an updated shockproof hammer image sample;
correspondingly, the image labeling is carried out on the shockproof hammer image sample according to a preset defect labeling rule to obtain the shockproof hammer labeling image sample, and the method comprises the following steps:
and carrying out image annotation on the target shockproof hammer in the updated shockproof hammer image sample according to a preset defect annotation rule to obtain a shockproof hammer annotation image sample.
Optionally, the image labeling is performed on the shockproof hammer image sample according to a preset defect labeling rule to obtain a shockproof hammer labeled image sample, including:
acquiring the type information of the vibration damper in the vibration damper image sample;
classifying the shockproof hammer image samples according to the shockproof hammer type information, and performing image annotation on classification results according to a preset annotation search box to obtain a first shockproof hammer image sample and a second shockproof hammer image sample;
and recording the first shockproof hammer image sample and the second shockproof hammer image sample as shockproof hammer labeling image samples.
Optionally, the recording the first and second anti-hammer image samples as anti-hammer labeling image samples includes:
acquiring the defect type of the second vibration damper image sample;
classifying the second anti-vibration hammer image sample according to the defect type to obtain a second anti-vibration hammer image sample classification result;
and recording the classification result of the first shockproof hammer image sample and the second shockproof hammer image sample as a shockproof hammer labeling image sample.
In addition, in order to achieve the above object, the present invention further provides a device for detecting a defect of a vibration damper, including:
the instruction analysis module is used for determining a to-be-detected area according to the defect detection instruction when the defect detection instruction is received;
the data transmission module is used for transmitting the defect detection instruction to image acquisition equipment so that the image acquisition equipment acquires an image to be detected of the area to be detected according to the defect detection instruction and feeds back the image to be detected;
the defect detection module is used for carrying out defect detection on the image to be detected through a preset vibration damper defect detection model to obtain a vibration damper defect detection result;
and the defect display module is used for determining the position information of the defective vibration damper according to the detection result of the vibration damper defect and displaying the position information of the defective vibration damper.
In addition, in order to achieve the above object, the present invention also provides a vibration damper defect detecting apparatus, including: a memory, a processor, and a stockbridge damper defect detection program stored on the memory and executable on the processor, the stockbridge damper defect detection program configured to implement the steps of the stockbridge damper defect detection method as described above.
In addition, to achieve the above object, the present invention further provides a storage medium having a vibration damper defect detection program stored thereon, which when executed by a processor, implements the steps of the vibration damper defect detection method as described above.
The invention discloses a method for determining a to-be-detected area according to a defect detection instruction when the defect detection instruction is received; transmitting the defect detection instruction to image acquisition equipment so that the image acquisition equipment acquires an image to be detected of the area to be detected according to the defect detection instruction and feeds back the image to be detected; performing defect detection on the image to be detected through a preset vibration damper defect detection model to obtain a vibration damper defect detection result; the method comprises the steps of determining a defect vibration damper position information according to a vibration damper defect detection result, displaying the defect vibration damper position information, determining a to-be-detected area according to a user defect detection instruction, controlling an image acquisition device to acquire an image of the to-be-detected area according to the defect detection instruction, transmitting the acquired image back to a terminal device, and detecting the defect through a preset vibration damper defect detection model to further obtain the vibration damper position information with the defect.
Drawings
FIG. 1 is a schematic structural diagram of a shockproof hammer defect detection device in a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating a method for detecting a defect in a vibration damper according to a first embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a shockproof hammer according to an embodiment of the method for detecting defects of a shockproof hammer of the present invention;
FIG. 4 is a schematic flow chart illustrating a method for detecting a defect in a vibration damper according to a second embodiment of the present invention;
FIG. 5 is a schematic flow chart illustrating a method for detecting a defect in a vibration damper according to a third embodiment of the present invention;
fig. 6 is a block diagram showing the structure of the first embodiment of the vibration damper defect detecting apparatus according to the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a vibration damper defect detection apparatus in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the vibration damper defect detecting apparatus may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in fig. 1 does not constitute a limitation of the stockbridge damper defect detecting apparatus and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a storage medium, may include therein an operating system, a network communication module, a user interface module, and a hammer damage detection program.
In the vibration damper defect detecting apparatus shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 of the apparatus for detecting a defect in a vibration damper according to the present invention may be provided in the apparatus for detecting a defect in a vibration damper, and the apparatus for detecting a defect in a vibration damper calls the program for detecting a defect in a vibration damper stored in the memory 1005 through the processor 1001, and executes the method for detecting a defect in a vibration damper according to the embodiment of the present invention.
An embodiment of the present invention provides a method for detecting a defect of a vibration damper, and referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of the method for detecting a defect of a vibration damper according to the present invention.
In this embodiment, the method for detecting the defect of the vibration damper includes the following steps:
step S10: and when a defect detection instruction is received, determining the area to be detected according to the defect detection instruction.
It should be noted that the main executing body of the method in this embodiment may be a vibration-proof hammer defect detecting device, where the vibration-proof hammer detecting device may be a device having functions of data communication, data processing, and data display, for example: the present embodiment is not limited to this, and in the present embodiment and the following embodiments, the control computer will be taken as an example for explanation.
It is worth mentioning that the defect detection instruction includes: the defect detection method includes the steps of acquiring information such as position information required to be subjected to defect detection, and information such as the number, angle and shooting parameters of images required to be acquired by image acquisition equipment, wherein the defect detection instruction is used for determining an area to be detected and can also be used for controlling the image acquisition equipment to perform image acquisition, the defect detection instruction can be operation information input by a user through a control computer, and the embodiment does not specifically limit the defect detection instruction.
It can be understood that the area to be detected refers to an area near a tower where the anti-vibration hammers exist, wherein the anti-vibration hammers are generally concentrated near the tower, but at least one anti-vibration hammer may exist at different heights of one tower, so that during one-time defect detection, an area to be detected needs to be determined according to a defect detection instruction of a user to facilitate image acquisition with follow-up procedures, and fig. 3 is a schematic diagram of an anti-vibration hammer structure.
Step S20: and transmitting the defect detection instruction to image acquisition equipment so that the image acquisition equipment acquires the image to be detected of the area to be detected according to the defect detection instruction and feeds back the image to be detected.
It should be understood that the image capturing device refers to a device for capturing images near a tower vibration damper, such as: the present embodiment does not specifically limit this, and in this embodiment and the following embodiments, the flying drone will be taken as an example for explanation.
In specific implementation, after receiving a defect detection instruction of a user, the control computer determines a to-be-detected area needing defect detection according to the defect detection instruction of the user, transmits the defect detection instruction to the unmanned aerial vehicle, so that the unmanned aerial vehicle acquires an image of the to-be-detected area, and feeds the acquired to-be-detected image back to the control computer.
Further, the quality of the captured image may be degraded due to the influence of the external environment, for example: the unmanned aerial vehicle may be influenced by wind when collecting the image, so that the unmanned aerial vehicle swings with the wind to cause image blurring, in the embodiment, the video image is firstly subjected to frame rate reduction and then the defects of the vibration damper and the vibration damper are detected in the routing inspection process of the unmanned aerial vehicle, and once the defects of the vibration damper or the vibration damper are detected, the frame rate detection is improved, and the defects of the vibration damper or the vibration damper cannot be detected for the same time, and then the frame rate detection is reduced. Therefore, the calculation cost and calculation time of detection can be reduced, the detection rate cannot be reduced, wherein when the unmanned aerial vehicle shoots an image, the unmanned aerial vehicle can also adopt a camera with a higher frame rate to reduce the exposure time and thus reduce the motion blur of the image, and can also use wiener filtering to reduce the influence of the motion blur on the image definition, and the embodiment does not specifically limit the method.
In addition, unmanned aerial vehicle can fly according to the route that contains in the defect detection instruction of user's on-the-spot output during the flight, stops to shoot the image detection stockbridge damper near the shaft tower slightly, and the unmanned aerial vehicle camera lens can be drawn close and zoom out, can make the shooting scope and be shot the stockbridge damper size and do the adjustment.
Step S30: and carrying out defect detection on the image to be detected through a preset vibration damper defect detection model to obtain a vibration damper defect detection result.
It should be noted that the preset stockbridge damper defect detection model is used for performing defect analysis on an image to be detected acquired by the unmanned aerial vehicle to obtain a defect analysis result, where the preset stockbridge damper defect detection model may be a pre-trained deep learning neural network, or may be another model with the same or similar function, and this embodiment is not particularly limited to this.
It can be understood that, in this embodiment, 12 residual error components may be used, and 1001 convolution kernels constitute a deep learning neural network to perform defect detection and classification on the stockbridge damper and the stockbridge damper, so as to obtain a preset stockbridge damper defect detection model, and a basic frame of the deep learning neural network may be divided into 4 parts, i.e., Input, backhaul, tack, and Prediction; 1. the Input part enriches a data set by splicing data enhancement, and has low requirement on hardware equipment and low calculation cost; 2. the backhaul part mainly comprises CSP modules, and feature extraction is carried out through CSPDarknet 53; 3. using FPN and a path aggregation network (PANet) in Neck to aggregate the image features at this stage; 4. finally, the network performs target prediction and outputs through prediction.
It should be understood that the detection result of the defect of the vibration damper may be obtained by performing defect analysis on a vibration damper image collected by the unmanned aerial vehicle, where the image analysis result may be divided into: normal, defective; and the vibration damper with defects can be further divided according to defect types, such as: skew, handle drop, and missing, etc., which are not specifically limited by the embodiment.
Step S40: and determining the position information of the defective vibration damper according to the detection result of the defect of the vibration damper, and displaying the position information of the defective vibration damper.
Note that the vibration damper position information is information such as the height, longitude, and latitude of the vibration damper.
In specific implementation, if the acquired image is detected to have defects through the preset stockbridge damper defect detection model, the position information of the stockbridge damper with the defects can be determined by acquiring the longitude, latitude and height information of the unmanned aerial vehicle with the picture, and the position information of the stockbridge damper with the defects is sent to the control computer or the client to be displayed to the user.
The embodiment discloses that when a defect detection instruction is received, a region to be detected is determined according to the defect detection instruction; transmitting the defect detection instruction to image acquisition equipment so that the image acquisition equipment acquires an image to be detected of the area to be detected according to the defect detection instruction and feeds back the image to be detected; performing defect detection on the image to be detected through a preset vibration damper defect detection model to obtain a vibration damper defect detection result; the method comprises the steps of determining a defect vibration damper position information according to a vibration damper defect detection result, displaying the defect vibration damper position information, determining a to-be-detected area according to a defect detection instruction of a user, controlling an image acquisition device to acquire an image of the to-be-detected area according to the defect detection instruction, transmitting the acquired image back to a terminal device, and performing defect detection through a preset vibration damper defect detection model to further acquire the vibration damper position information with defects.
Referring to fig. 4, fig. 4 is a schematic flow chart illustrating a method for detecting a shock absorber defect according to a second embodiment of the present invention.
Based on the first embodiment, in this embodiment, the step S30 includes:
step S301: and acquiring a storage path and an image name corresponding to the image to be detected.
It should be noted that, after the unmanned aerial vehicle collects the image of the area to be detected of the tower according to the defect detection instruction of the user, the collected image is fed back to the preset storage area in the control computer for storage through data transmission, where the preset storage area may be a computer hard disk or an external usb disk, and the embodiment is not particularly limited to this.
It should be understood that the image name of the image to be detected refers to the name of the image to be detected in the computer hard disk when the image to be detected is stored; the storage path of the image to be detected refers to an index path corresponding to the storage position of the image to be detected in the computer, for example: the image to be detected is located in a photo folder in a disk C in a computer hard disk, and the corresponding storage path is local computer/local disk (C)/photo.
Step S302: and generating a defect detection message according to the storage path and the image name.
It can be understood that, after the image to be detected is successfully stored, the preset stockbridge damper defect detection model cannot automatically read the image to be detected to perform image defect analysis, at this time, a defect detection message can be obtained by packing the image name and the storage path corresponding to the image to be detected, and the defect detection message is sent to the preset stockbridge damper defect detection model, wherein, in order to facilitate data transmission and confidentiality, the data format of the defect detection message can be json format, which is not specifically limited in this embodiment.
Step S303: and carrying out defect detection through a preset vibration damper defect detection model according to the defect detection message to obtain a vibration damper defect detection result.
It should be noted that, after the preset stockbridge damper defect detection model receives the defect detection message, the image to be detected is extracted through the storage path and the image name in the defect detection message, and the defect detection is performed on the image to judge whether the stockbridge damper in the image has a defect.
Further, a plurality of vibration dampers may exist in the same image, and therefore a plurality of defect detection results may occur in the detection of the defect of the vibration damper in one image, and in order to obtain the most accurate detection result, the step S303 includes:
determining a target image according to the defect detection message, and acquiring characteristic information of the target image;
performing defect detection on the target image through a preset stockbridge damper defect detection model based on the characteristic information and a preset search frame to obtain an initial defect detection result;
and acquiring a category confidence coefficient threshold corresponding to the initial defect detection result, and determining a vibration damper defect detection result according to the category confidence coefficient threshold.
It can be understood that the characteristic information refers to integrity information and the like of the vibration dampers in the image to be detected, and the preset search frame can be a frame diagram matched with the sizes of the vibration dampers, wherein, even if a plurality of vibration dampers exist in one image, the sizes of the vibration dampers in the image are different, and the defect detection can be accurately performed on each vibration damper by selecting the search frames with different sizes, so that a more accurate vibration damper defect detection result is obtained.
It should be understood that the category confidence threshold is used for extracting the most appropriate defect detection result obtained by the preset stockbridge damper defect detection model in the same image, that is, the category number corresponding to the maximum confidence threshold is output when stockbridge damper defects at the same position of the tower are detected, so that the detection rate and the recognition rate are improved.
The embodiment discloses obtaining a storage path and an image name corresponding to the image to be detected; generating a defect detection message according to the storage path and the image name; and carrying out defect detection through a preset stockbridge damper defect detection model according to the defect detection message, and obtaining a stockbridge damper defect detection result, wherein the defect detection is carried out by sending a storage path and an image name corresponding to the image stored in the local hard disk to the preset stockbridge damper defect detection model, so that the efficiency of reading the image by the preset stockbridge damper defect detection model is higher and more accurate, and the defect detection efficiency and accuracy are improved.
Referring to fig. 5, fig. 5 is a schematic flow chart of a method for detecting a defect of a vibration damper according to a third embodiment of the present invention.
Based on the first embodiment, in this embodiment, before the step S30, the method further includes:
step S210: a jar hammer image sample is obtained.
It should be noted that the vibration damper image samples refer to various vibration damper images collected in advance, wherein the vibration damper image samples include a defect-free vibration damper image and a defect-free vibration damper image, and the vibration damper image samples may be image samples corresponding to different types of vibration dampers, different signal vibration dampers and vibration dampers with different defect degrees.
In specific implementation, 20000 shockproof hammer image samples can be adopted to achieve a better training effect, and the number of samples can be increased by adopting image rotation, overturning and mosaic enhancing methods to increase the number of situations covered by training samples, so that the detection rate is improved.
Step S220: and carrying out image annotation on the shockproof hammer image sample according to a preset defect annotation rule to obtain the shockproof hammer annotation image sample.
It should be understood that the shockproof hammer labeling image sample is obtained by framing the shockproof hammer in the shockproof hammer image sample in a search box with a proper size, wherein during the framing, the complete shockproof hammer frame needs to be selected, for example: when a handle-falling vibration damper is selected in a frame, the handle-falling part is also selected in a frame in a search frame, if the image cannot be completely collected, the vibration damper can be filtered in a screening mode, and meanwhile, the vibration damper with the complete frame line can be distinguished from the vibration damper with the incomplete display at the peripheral edge of the image.
It should be noted that the default defect labeling rule may be that the labeling is not performed because it is not possible to determine whether the vibration damper is complete or falls due to the fact that the vibration damper with incomplete display at the peripheral edge of the image is not displayed. Further, in the detection stage, the detection results of the vibration dampers or the defects of the vibration dampers within a certain range around the periphery of the image are filtered out and are not taken as the final detection results.
Further, before the step S220, the method further includes;
performing overlapping detection on the shockproof hammer image sample to obtain a detection result;
when the detection result is that the shockproof hammer image samples are overlapped, determining a target shockproof hammer and an overlapped shockproof hammer;
acquiring a background color in the shockproof hammer image sample, and updating the overlapped shockproof hammers in the shockproof hammer image sample according to the background color to obtain an updated shockproof hammer image sample;
correspondingly, the image labeling is carried out on the shockproof hammer image sample according to a preset defect labeling rule to obtain the shockproof hammer labeling image sample, and the method comprises the following steps:
and carrying out image annotation on the target vibration damper in the updated vibration damper image sample according to a preset defect annotation rule to obtain a vibration damper annotation image sample.
It should be understood that the detection of the overlap refers to detecting whether there is an occluded stockbridge in the image; the target vibration damper refers to a complete vibration damper in the image to be detected and needs defect detection, and the overlapped vibration damper refers to a vibration damper shielded by a target or other objects in the image to be detected.
In the specific implementation, if overlapping detection is performed on the image to be detected, the existence of the shielded vibration damper in the image to be detected is detected, at this time, the shielded vibration damper can be smeared according to the background color to eliminate the overlapped vibration damper, only the vibration damper which is not shielded is left, and the smeared image to be detected is marked to obtain a vibration damper marked image sample.
Further, in order to improve the defect detection efficiency and accuracy of the preset stockbridge damper defect detection model, the step S220 includes:
acquiring the type information of the vibration damper in the vibration damper image sample;
classifying the shockproof hammer image samples according to the shockproof hammer type information, and performing image annotation on classification results according to a preset annotation search box to obtain a first shockproof hammer image sample and a second shockproof hammer image sample;
and recording the first shockproof hammer image sample and the second shockproof hammer image sample as shockproof hammer labeling image samples.
Note that the anti-vibration hammer type information includes: and in the process of marking samples, different types of vibration dampers are marked and classified according to types, so that the detection rate of the training model can be improved, wherein the first vibration damper image sample is a vibration damper image sample without defects normally, and the second vibration damper image sample is a vibration damper image sample with defects.
Meanwhile, for the shakeproof hammer with defects, labeling and classifying can be performed according to the defect type of the shakeproof hammer, namely, the step of recording the first shakeproof hammer image sample and the second shakeproof hammer image sample as the shakeproof hammer labeling image samples comprises the following steps:
acquiring the defect type of the second vibration damper image sample;
classifying the second anti-vibration hammer image sample according to the defect type to obtain a second anti-vibration hammer image sample classification result;
and recording the classification result of the first shockproof hammer image sample and the second shockproof hammer image sample as a shockproof hammer labeling image sample.
It is to be understood that, in the present embodiment, the defect type may be a slanting of the hammer, a falling of the hammer, or the like, and the present embodiment does not specifically limit this.
Step S230: and carrying out model training on the shockproof hammer image sample and the shockproof hammer labeling image sample through an initial neural network model to obtain a preset shockproof hammer defect detection model.
It can be understood that the initial neural network model may be a lightweight deep learning neural network with a smaller number of convolution layers, or may be other neural network models with the same or similar functions, which is not limited in this embodiment.
The embodiment discloses obtaining a shockproof hammer image sample; carrying out image annotation on the shockproof hammer image sample according to a preset defect annotation rule to obtain a shockproof hammer annotation image sample; and carrying out model training on the shockproof hammer image sample and the shockproof hammer labeling image sample through an initial neural network model to obtain a preset shockproof hammer defect detection model.
In addition, an embodiment of the present invention further provides a storage medium, where the storage medium stores a stockbridge damper defect detecting program, and the stockbridge damper defect detecting program, when executed by a processor, implements the steps of the stockbridge damper defect detecting method as described above.
Since the storage medium adopts all technical solutions of all the embodiments, at least all the beneficial effects brought by the technical solutions of the embodiments are achieved, and no further description is given here.
Referring to fig. 6, fig. 6 is a block diagram showing a structure of a vibration damper defect detecting apparatus according to a first embodiment of the present invention.
As shown in fig. 6, the apparatus for detecting a defect in a vibration damper according to an embodiment of the present invention includes:
and the instruction analysis module 10 is configured to determine the region to be detected according to the defect detection instruction when the defect detection instruction is received.
And the data transmission module 20 is configured to transmit the defect detection instruction to an image acquisition device, so that the image acquisition device acquires an image to be detected of the area to be detected according to the defect detection instruction, and feeds back the image to be detected.
And the defect detection module 30 is used for carrying out defect detection on the image to be detected through a preset vibration damper defect detection model to obtain a vibration damper defect detection result.
And the defect display module 40 is used for determining the position information of the defective vibration damper according to the detection result of the vibration damper defect and displaying the position information of the defective vibration damper.
The embodiment discloses that when a defect detection instruction is received, a region to be detected is determined according to the defect detection instruction; transmitting the defect detection instruction to image acquisition equipment so that the image acquisition equipment acquires an image to be detected of the area to be detected according to the defect detection instruction and feeds back the image to be detected; performing defect detection on the image to be detected through a preset vibration damper defect detection model to obtain a vibration damper defect detection result; the method comprises the steps of determining a defective vibration damper position information according to a vibration damper defect detection result, displaying the defective vibration damper position information, determining a to-be-detected area according to a user defect detection instruction, controlling an image acquisition device to acquire an image of the to-be-detected area according to the defect detection instruction, transmitting the acquired image back to a terminal device, and performing defect detection through a preset vibration damper defect detection model to further obtain the vibration damper position information with defects.
In an embodiment, the defect detection module 30 is further configured to obtain a storage path and an image name corresponding to the image to be detected; generating a defect detection message according to the storage path and the image name; and carrying out defect detection through a preset vibration damper defect detection model according to the defect detection message to obtain a vibration damper defect detection result.
In an embodiment, the defect detection module 30 is further configured to determine a target image according to the defect detection message, and obtain feature information of the target image; performing defect detection on the target image through a preset stockbridge damper defect detection model based on the characteristic information and a preset search frame to obtain an initial defect detection result; and acquiring a category confidence coefficient threshold corresponding to the initial defect detection result, and determining a vibration damper defect detection result according to the category confidence coefficient threshold.
In an embodiment, the defect detecting module 30 is further configured to obtain a vibration damper image sample; carrying out image annotation on the shockproof hammer image sample according to a preset defect annotation rule to obtain a shockproof hammer annotation image sample; and carrying out model training on the vibration damper image sample and the vibration damper labeling image sample through an initial neural network model to obtain a preset vibration damper defect detection model.
In an embodiment, the defect detecting module 30 is further configured to perform overlapping detection on the shockproof hammer image sample to obtain a detection result; when the detection result is that the shockproof hammer image samples are overlapped, determining a target shockproof hammer and an overlapped shockproof hammer; acquiring a background color in the shockproof hammer image sample, and updating the overlapped shockproof hammers in the shockproof hammer image sample according to the background color to obtain an updated shockproof hammer image sample; correspondingly, the image labeling is carried out on the shockproof hammer image sample according to a preset defect labeling rule to obtain the shockproof hammer labeling image sample, and the method comprises the following steps: and carrying out image annotation on the target vibration damper in the updated vibration damper image sample according to a preset defect annotation rule to obtain a vibration damper annotation image sample.
In an embodiment, the defect detecting module 30 is further configured to obtain the type information of the anti-vibration hammer in the anti-vibration hammer image sample; classifying the shockproof hammer image samples according to the shockproof hammer type information, and performing image annotation on classification results according to a preset annotation search box to obtain a first shockproof hammer image sample and a second shockproof hammer image sample; and recording the first shockproof hammer image sample and the second shockproof hammer image sample as shockproof hammer labeling image samples.
In an embodiment, the defect detection module 30 is further configured to obtain a defect type of the second anti-vibration hammer image sample; classifying the second shockproof hammer image sample according to the defect type to obtain a second shockproof hammer image sample classification result; and recording the classification result of the first shockproof hammer image sample and the second shockproof hammer image sample as a shockproof hammer labeling image sample.
It should be understood that the above is only an example, and the technical solution of the present invention is not limited in any way, and in a specific application, a person skilled in the art may set the technical solution as needed, and the present invention is not limited thereto.
It should be noted that the above-described work flows are only exemplary, and do not limit the scope of the present invention, and in practical applications, a person skilled in the art may select some or all of them to achieve the purpose of the solution of the embodiment according to actual needs, and the present invention is not limited herein.
In addition, the technical details that are not described in detail in this embodiment may be referred to the method for detecting a defect of a vibration damper provided in any embodiment of the present invention, and are not described herein again.
Further, it is to be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention or portions thereof that contribute to the prior art may be embodied in the form of a software product, where the computer software product is stored in a storage medium (e.g. Read Only Memory (ROM)/RAM, magnetic disk, optical disk), and includes several instructions for enabling a terminal device (e.g. a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention, and all equivalent structures or equivalent processes performed by the present invention or directly or indirectly applied to other related technical fields are also included in the scope of the present invention.
Claims (10)
1. A method for detecting defects of a vibration damper is characterized by comprising the following steps:
when a defect detection instruction is received, determining a region to be detected according to the defect detection instruction;
transmitting the defect detection instruction to image acquisition equipment so that the image acquisition equipment acquires an image to be detected of the area to be detected according to the defect detection instruction and feeds back the image to be detected;
performing defect detection on the image to be detected through a preset vibration damper defect detection model to obtain a vibration damper defect detection result;
and determining the position information of the defective vibration damper according to the detection result of the defect of the vibration damper, and displaying the position information of the defective vibration damper.
2. The method for detecting the defect of the vibration damper according to claim 1, wherein the step of performing defect detection on the image to be detected through a preset vibration damper defect detection model to obtain a vibration damper defect detection result comprises:
acquiring a storage path and an image name corresponding to the image to be detected;
generating a defect detection message according to the storage path and the image name;
and performing defect detection through a preset stockbridge damper defect detection model according to the defect detection message to obtain a stockbridge damper defect detection result.
3. The method for detecting the defect of the anti-vibration hammer according to claim 2, wherein the step of detecting the defect according to the defect detection message by using a preset anti-vibration hammer defect detection model to obtain an anti-vibration hammer defect detection result comprises:
determining a target image according to the defect detection message, and acquiring characteristic information of the target image;
performing defect detection on the target image through a preset stockbridge damper defect detection model based on the characteristic information and a preset search frame to obtain an initial defect detection result;
and acquiring a category confidence coefficient threshold corresponding to the initial defect detection result, and determining a vibration damper defect detection result according to the category confidence coefficient threshold.
4. The method for detecting a defect of a vibration damper according to claim 1, wherein before the defect detection of the image to be detected is performed by using the preset vibration damper defect detection model to obtain the vibration damper defect detection result, the method further comprises:
acquiring a shockproof hammer image sample;
carrying out image annotation on the shockproof hammer image sample according to a preset defect annotation rule to obtain a shockproof hammer annotation image sample;
and carrying out model training on the vibration damper image sample and the vibration damper labeling image sample through an initial neural network model to obtain a preset vibration damper defect detection model.
5. The method for detecting a defect of a vibration damper according to claim 4, wherein before the image labeling is performed on the vibration damper image sample according to a preset defect labeling rule to obtain the vibration damper labeled image sample, the method further comprises:
performing overlapping detection on the shockproof hammer image sample to obtain a detection result;
when the detection result is that the shockproof hammer image samples are overlapped, determining a target shockproof hammer and an overlapped shockproof hammer;
acquiring a background color in the shockproof hammer image sample, and updating the overlapped shockproof hammers in the shockproof hammer image sample according to the background color to obtain an updated shockproof hammer image sample;
correspondingly, the image labeling is carried out on the shockproof hammer image sample according to a preset defect labeling rule to obtain the shockproof hammer labeling image sample, and the method comprises the following steps:
and carrying out image annotation on the target shockproof hammer in the updated shockproof hammer image sample according to a preset defect annotation rule to obtain a shockproof hammer annotation image sample.
6. The method for detecting a defect of a vibration damper according to claim 4, wherein the image labeling of the vibration damper image sample according to a preset defect labeling rule to obtain a vibration damper labeled image sample comprises:
acquiring the type information of the vibration damper in the vibration damper image sample;
classifying the shockproof hammer image samples according to the shockproof hammer type information, and carrying out image annotation on classification results according to a preset annotation search box to obtain a first shockproof hammer image sample and a second shockproof hammer image sample;
and recording the first shockproof hammer image sample and the second shockproof hammer image sample as shockproof hammer labeling image samples.
7. The method of claim 6, wherein the recording the first and second shockproof hammer image samples as shockproof hammer marking image samples comprises:
acquiring the defect type of the second vibration damper image sample;
classifying the second shockproof hammer image sample according to the defect type to obtain a second shockproof hammer image sample classification result;
and recording the classification result of the first shockproof hammer image sample and the second shockproof hammer image sample as a shockproof hammer labeling image sample.
8. A vibration damper defect detecting apparatus, characterized in that the vibration damper defect detecting apparatus comprises:
the instruction analysis module is used for determining a to-be-detected area according to the defect detection instruction when the defect detection instruction is received;
the data transmission module is used for transmitting the defect detection instruction to image acquisition equipment so that the image acquisition equipment acquires an image to be detected of the area to be detected according to the defect detection instruction and feeds back the image to be detected;
the defect detection module is used for carrying out defect detection on the image to be detected through a preset vibration damper defect detection model to obtain a vibration damper defect detection result;
and the defect display module is used for determining the position information of the defective vibration damper according to the detection result of the vibration damper defect and displaying the position information of the defective vibration damper.
9. A vibration damper defect detecting apparatus, characterized in that the vibration damper defect detecting apparatus comprises: a memory, a processor, and a stockbridge damper defect detection program stored on the memory and executable on the processor, the stockbridge damper defect detection program configured to implement the stockbridge damper defect detection method of any one of claims 1 to 7.
10. A storage medium having a hammer-proof defect detection program stored thereon, the hammer-proof defect detection program, when executed by a processor, implementing the hammer-proof defect detection method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210259897.4A CN114693614A (en) | 2022-03-16 | 2022-03-16 | Defect detection method, device and equipment for vibration damper and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210259897.4A CN114693614A (en) | 2022-03-16 | 2022-03-16 | Defect detection method, device and equipment for vibration damper and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114693614A true CN114693614A (en) | 2022-07-01 |
Family
ID=82139174
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210259897.4A Pending CN114693614A (en) | 2022-03-16 | 2022-03-16 | Defect detection method, device and equipment for vibration damper and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114693614A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116229278A (en) * | 2023-05-10 | 2023-06-06 | 广东电网有限责任公司珠海供电局 | Method and system for detecting rust defect of vibration damper of power transmission line |
| CN116593479A (en) * | 2023-07-19 | 2023-08-15 | 北京阿丘机器人科技有限公司 | Method, device, equipment and storage medium for detecting appearance quality of battery cover plate |
-
2022
- 2022-03-16 CN CN202210259897.4A patent/CN114693614A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116229278A (en) * | 2023-05-10 | 2023-06-06 | 广东电网有限责任公司珠海供电局 | Method and system for detecting rust defect of vibration damper of power transmission line |
| CN116229278B (en) * | 2023-05-10 | 2023-08-04 | 广东电网有限责任公司珠海供电局 | Method and system for detecting rust defect of vibration damper of power transmission line |
| CN116593479A (en) * | 2023-07-19 | 2023-08-15 | 北京阿丘机器人科技有限公司 | Method, device, equipment and storage medium for detecting appearance quality of battery cover plate |
| CN116593479B (en) * | 2023-07-19 | 2024-02-06 | 北京阿丘机器人科技有限公司 | Method, device, equipment and storage medium for detecting appearance quality of battery cover plate |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10984293B2 (en) | Image processing method and apparatus | |
| CN110569695B (en) | Image processing method and device based on loss assessment image judgment model | |
| CN111507958B (en) | Target detection method, training method of detection model and electronic equipment | |
| CN110705405B (en) | Target labeling method and device | |
| US20200349687A1 (en) | Image processing method, device, unmanned aerial vehicle, system, and storage medium | |
| WO2021082662A1 (en) | Method and apparatus for assisting user in shooting vehicle video | |
| US11676257B2 (en) | Method and device for detecting defect of meal box, server, and storage medium | |
| WO2020042800A1 (en) | Auxiliary method for capturing damage assessment image of vehicle, device, and apparatus | |
| CN114693614A (en) | Defect detection method, device and equipment for vibration damper and storage medium | |
| US9607236B1 (en) | Method and apparatus for providing loan verification from an image | |
| EP3428840A1 (en) | Computer implemented detecting method, computer implemented learning method, detecting apparatus, learning apparatus, detecting system, and recording medium | |
| US20130279758A1 (en) | Method and system for robust tilt adjustment and cropping of license plate images | |
| US10242284B2 (en) | Method and apparatus for providing loan verification from an image | |
| US20180336433A1 (en) | Reading Test Cards Using a Mobile Device | |
| US11164028B2 (en) | License plate detection system | |
| US20220198609A1 (en) | Modifying sensor data using generative adversarial models | |
| CN110505497B (en) | Cloud mobile phone operation monitoring method, system, device and storage medium | |
| CN113052151A (en) | Unmanned aerial vehicle automatic landing guiding method based on computer vision | |
| CN112465856A (en) | Unmanned aerial vehicle-based ship track correction method and device and electronic equipment | |
| CN114724246A (en) | Dangerous behavior identification method and device | |
| US20220171981A1 (en) | Recognition of license plate numbers from bayer-domain image data | |
| CN113128522A (en) | Target identification method and device, computer equipment and storage medium | |
| CN113505780A (en) | Two-dimensional code-based intelligent detection maintenance method and equipment | |
| JP2019067106A (en) | Image processing device, image processing method, and program | |
| US20200077016A1 (en) | Automated Image Capture System with Expert Guidance |
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 |