CN112924466B - Underwater nondestructive inspection equipment based on combination of vision and magnetic powder and processing method - Google Patents
Underwater nondestructive inspection equipment based on combination of vision and magnetic powder and processing method Download PDFInfo
- Publication number
- CN112924466B CN112924466B CN202110261616.4A CN202110261616A CN112924466B CN 112924466 B CN112924466 B CN 112924466B CN 202110261616 A CN202110261616 A CN 202110261616A CN 112924466 B CN112924466 B CN 112924466B
- Authority
- CN
- China
- Prior art keywords
- underwater
- nondestructive inspection
- image
- pipeline
- module
- 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.)
- Active
Links
- 238000007689 inspection Methods 0.000 title claims abstract description 56
- 239000006247 magnetic powder Substances 0.000 title claims abstract description 25
- 238000003672 processing method Methods 0.000 title claims abstract description 14
- 239000000725 suspension Substances 0.000 claims abstract description 37
- 238000004891 communication Methods 0.000 claims abstract description 15
- 238000001179 sorption measurement Methods 0.000 claims description 20
- 230000007547 defect Effects 0.000 claims description 19
- 238000001514 detection method Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 14
- 238000013145 classification model Methods 0.000 claims description 13
- 239000007921 spray Substances 0.000 claims description 8
- 239000007788 liquid Substances 0.000 claims description 7
- 239000006249 magnetic particle Substances 0.000 abstract description 10
- 238000005507 spraying Methods 0.000 abstract description 3
- 230000000007 visual effect Effects 0.000 abstract description 3
- 238000000034 method Methods 0.000 description 6
- 239000003086 colorant Substances 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000005314 correlation function Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000003466 welding Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000005381 potential energy Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000000518 rheometry Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63C—LAUNCHING, HAULING-OUT, OR DRY-DOCKING OF VESSELS; LIFE-SAVING IN WATER; EQUIPMENT FOR DWELLING OR WORKING UNDER WATER; MEANS FOR SALVAGING OR SEARCHING FOR UNDERWATER OBJECTS
- B63C11/00—Equipment for dwelling or working underwater; Means for searching for underwater objects
- B63C11/52—Tools specially adapted for working underwater, not otherwise provided for
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N27/00—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means
- G01N27/72—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables
- G01N27/82—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables for investigating the presence of flaws
- G01N27/83—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables for investigating the presence of flaws by investigating stray magnetic fields
- G01N27/84—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables for investigating the presence of flaws by investigating stray magnetic fields by applying magnetic powder or magnetic ink
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- 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
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30152—Solder
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Pathology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Signal Processing (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Electrochemistry (AREA)
- Mechanical Engineering (AREA)
- Ocean & Marine Engineering (AREA)
- Quality & Reliability (AREA)
- Investigating Or Analyzing Materials By The Use Of Magnetic Means (AREA)
Abstract
The invention discloses an underwater nondestructive inspection device based on combination of vision and magnetic powder and a processing method, which adopt the mode of combining the magnetic powder and the vision to carry out inspection operation for underwater pipelines, and the underwater nondestructive inspection device comprises: the underwater nondestructive inspection device is fixed on the underwater movable platform; wherein the underwater nondestructive inspection device mainly comprises: the movable underwater platform mainly comprises a motion control module. The invention adopts the motion control module to realize the positioning and the movement of the underwater movable platform; the control module of the flaw detector is adopted to realize the spraying of the magnetic suspension; acquiring image information before and after the underwater magnetic particle flaw detector adsorbs a pipeline by using a camera module; uploading position information and image information by adopting a communication module; by extracting and fusing high-level semantic information to the magnetic powder inspection data and the visual image data, the autonomous inspection and nondestructive inspection of the underwater pipeline are realized.
Description
Technical Field
The invention relates to the technical field of underwater nondestructive inspection, in particular to an underwater nondestructive inspection device based on the combination of vision and magnetic powder and a processing method.
Background
With the continuous development of marine resources, more and more mobile devices and fixing devices are arranged on the sea, underwater pipelines are also in explosive growth for facilitating energy transportation, and when the submarine pipelines are not buried deeply enough, the submarine wave flow repeatedly scours to cause fatigue damage to pipeline joints; the impact of the ship anchor or the falling object on the ship can also cause pipeline damage, and the pipeline can be broken when the impact is serious; if a pipeline is laid on an unstable seabed having a large rheology, such as a sandy seabed, the pipeline may collapse, slide, and erode to cause strength or deformation failure. Therefore, the subsea pipeline needs to be serviced periodically.
The traditional pipeline underwater nondestructive inspection technology mainly depends on manual submerged inspection, operators need to finish detection operation on the seabed for a long time, the process has great requirements on physical quality of the operators, detection results are uneven, research on related underwater flaw detectors mostly relates to the flow of autonomous flaw detection and image information transmission of the underwater flaw detectors, image analysis still needs to be finished manually, and a new solution is urgently needed at present.
Disclosure of Invention
The invention aims to provide an underwater nondestructive inspection device based on combination of vision and magnetic powder and a processing method thereof, so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme: the underwater nondestructive inspection equipment based on the combination of vision and magnetic powder comprises an underwater nondestructive inspection device and an underwater movable platform, wherein the underwater nondestructive inspection device is specified on the underwater movable platform; the underwater nondestructive inspection device mainly comprises an inspection instrument control module, a camera module, a communication module and an image processing module, wherein the inspection instrument control module is respectively connected with the camera module, the communication module and the image processing module, the underwater movable platform mainly comprises a motion control module, the motion control module comprises a depth meter, a gyroscope, a magnetometer, a universal wheel, an adsorption device and a propeller, the depth meter, the gyroscope and the magnetometer are all fixed on the underwater movable platform, the universal wheel is installed at the bottom of the underwater movable platform, and the adsorption device and the propeller are all installed at the bottom of the underwater movable platform.
Preferably, nondestructive inspection device still includes universal joint, hose, magnetic suspension shower head and magnetic particle inspection appearance under water, but magnetic particle inspection appearance, hose and camera module pass through the universal joint to be fixed on portable platform under water, through adjusting each module angle of universal joint adjustment, magnetic suspension sprays through hose and magnetic suspension shower head.
Preferably, the treatment method comprises the following steps:
s1, positioning and adsorbing an underwater nondestructive inspection real-time control system on a pipeline based on a motion control module, and feeding back pose information;
s2, the underwater nondestructive inspection real-time control system inspects the workpiece and sprays magnetic suspension;
s3, the underwater nondestructive inspection real-time control system inspects the workpiece, and acquires and uploads image information with magnetic suspension;
s4, the underwater nondestructive inspection real-time control system inspects the workpiece, and the flaw detector adsorbs magnetic suspension;
s5, an underwater nondestructive inspection real-time control system inspects the workpiece, and acquires and uploads image information after magnetic powder adsorption;
s6, comparing the images before and after adsorption to find out difference points;
s7, marking difference point images based on structural similarity, gray difference and color richness;
and S8, clustering the preprocessed images based on the MCF-VGG image classification model and uploading.
Preferably, step S1 specifically includes: the motion control module adjusts the relative adsorption force between the adsorption module and the pipeline to realize the adsorption function, and through the universal wheel and the control of the propeller, the device can move on the pipeline, and the position of the device finally adsorbed on the pipeline is transmitted to the PC through the communication module.
Preferably, step S3 is: when the motion control module patrols the pipeline for one week, the camera module records an image of the pipeline for one week, generates a panoramic image of the underwater pipeline after the magnetic suspension liquid is sprayed, and uploads pipeline image information to the PC through the communication module.
Preferably, step S6 is: the image information after the magnetic suspension is sprayed and adsorbed is compared, and the damage images are classified through the image processing module.
Preferably, step S7 is: based on the image processing module, by comparing the image information before and after the magnetic suspension liquid is sprayed, based on the three characteristics of image structure similarity, gray difference and color richness, the images are pre-classified by considering that the magnetic suspension liquid residue exists at the defect position and is close to black.
Preferably, step S8 is: based on the image processing module, considering that the local similarity of the images after the magnetic suspension liquid is sprayed is strong, the classified images are classified through the MCF-VGG image classification model clustering characteristics, and then the classified images are correspondingly marked.
Compared with the prior art, the invention has the beneficial effects that: the device and the method provided by the invention realize the integrated operation flow of underwater magnetic powder and visual nondestructive flaw detection, and the MCF-VGG image classification model is adopted to classify the detected damage, compared with manual flaw detection, the device and the method have clear quantitative indexes, thereby fundamentally solving the influence of the professional level of workers on the damage detection rate and greatly improving the flaw detection effect of underwater magnetic powder flaw detection.
Drawings
FIG. 1 is a flow chart of an underwater nondestructive inspection device and a processing method based on the combination of vision and magnetic powder provided by the invention;
FIG. 2 is a mechanical structure diagram of an underwater nondestructive inspection device and a processing method based on the combination of vision and magnetic powder provided by the invention;
reference numerals: 1. a depth meter; 2. a gyroscope; 3. a magnetic particle flaw detector; 4. a universal wheel; 5. a magnetometer; 6. a camera module; 7. a universal joint; 8. an adsorption device; 9. a communication module; 10. a propeller; 11. a hose; 12. magnetic suspension shower head.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. 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.
In the description of the present invention, it should be noted that the terms "upper", "lower", "inner", "outer", "front", "rear", "both ends", "one end", "the other end", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it is to be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "disposed," "connected," and the like are to be construed broadly, such as "connected," which may be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Referring to fig. 1, the present invention provides a technical solution: the underwater nondestructive inspection equipment based on the combination of vision and magnetic powder comprises the following steps:
s1: positioning based on the motion control module, adsorbing on the pipeline, and feeding back the position of the motion control module;
the underwater movable platform mainly comprises a motion control module, and the motion control module consists of a depth meter 1, a gyroscope 2, a magnetometer 5, a universal wheel 4, an adsorption device 8 and a propeller 10. The underwater nondestructive inspection device is composed of a magnetic particle inspection instrument 3, a camera module 6, a universal joint 7, a hose 11, a magnetic suspension spray head 12 and a communication module 9, wherein the magnetic particle inspection instrument 3, the camera module 6 and the hose 11 are fixed on an underwater movable platform through the universal joint 7, and the magnetic suspension is sprayed through the hose 11 and the magnetic suspension spray head 12.
The underwater movable platform can realize the function that the system is adsorbed on the pipeline to move by controlling the relative adsorption force of the pipeline and the speed of the propeller. Through the data detected by the depth meter, the gyroscope, the accelerometer and the magnetometer, a negative feedback function based on position information can be realized, and the correction of the system position is realized.
S2: the underwater nondestructive inspection real-time control system inspects the workpiece for one circle and sprays magnetic suspension;
the system adsorbs the pipeline for a circle by adjusting the relative adsorption force between the system and the pipeline and controlling the propeller, and the effect of spraying the magnetic suspension on the pipeline can be ensured by adjusting the deflection angle of the movable joint between the system and each module.
S3: the underwater nondestructive inspection real-time control system inspects workpieces, acquires image information and uploads the image information;
the system is adsorbed on the pipeline to inspect the pipeline for a circle by adjusting the relative adsorption force between the system and the pipeline and controlling the propeller, and meanwhile, the camera module shoots pipeline image information sprayed with magnetic suspension and uploads the image information to the PC through the communication module.
S4: the underwater nondestructive inspection real-time control system inspects the workpiece and opens the flaw detector to adsorb magnetic suspension;
the system adsorbs the pipeline for a week through the relative adsorption affinity between adjustment and the pipeline and to the control of propeller, patrols and examines the pipeline through flaw detector control module and starts magnetic particle flaw detector simultaneously, adsorbs spraying magnetic suspension.
S5: the underwater nondestructive inspection real-time control system inspects the workpiece, and acquires and uploads image information again;
the system is adsorbed on the pipeline to inspect the pipeline for a circle by adjusting the relative adsorption force between the system and the pipeline and controlling the propeller, meanwhile, the camera module shoots pipeline image information of magnetic suspension adsorbed by the magnetic particle flaw detector, and the image information is uploaded to the PC through the communication module.
S6, comparing the images before and after adsorption to find out difference points;
s7, marking difference point images based on structural similarity, gray difference and color richness;
based on image information before and after the magnetic particle flaw detector is adsorbed, which is obtained by the camera module and the communication module, a structural similarity index of the image is constructed, the image before and after the image is compared, and the position where magnetic suspension exists, namely the position where a defect exists, is marked.
The image processing module is carried out at a PC (personal computer) end, the image processing comprises constructing structural similarity index mark difference points of an image, pre-classifying through gray level difference and color richness of the image, and classifying defects by adopting an MCF-VGG (micro-computer graphics context) image classification model. The structural similarity uses the following formula:
in the structural similarity formula, muxIs the mean value of the image x, μyIs the mean value, σ, of the image yx 2Is the variance, σ, of the image xy 2Is the variance, σ, of the image yxyIs the covariance of the images x and y, c1And c2To maintain a stable constant.
In the structural similarity formula, the mean value is used as the brightness estimation, the standard deviation is used as the contrast estimation, and the covariance is used as the measurement of the structural similarity degree. The smaller the value of SSIM, the worse the inter-image similarity.
Acquiring image information of a pipeline defect after the magnetic particle flaw detector is adsorbed based on a camera module, uploading the image information to a PC (personal computer) terminal based on a communication module, constructing an image model of the pipeline defect by an image processing module, carrying out digital processing on the image, and establishing a gray difference formula as follows:
in the formula of the gray scale difference degree, D is the gray scale difference degree, DiThe square sum of the difference between the RGB three values of the ith pixel and the average value of the RGB three values is obtained, and N is the number of pixels in the image. In the formula, d is specifically:
in the gray value formula, R is the value of each pixel in the red channel, G is the value of each pixel in the green channel, B is the value of each pixel in the blue channel, and average is the average value of each pixel in R, G, B channels. Average in the formula is as follows:
in the constructed gray difference formula, if the average value of the RGB three values is closer to 255, the image is closer to no color, and if the average value of the RGB three values is closer to 0, the image is closer to black; if the RGB three-value difference is large, the image presents a certain color.
In the gray level difference degree formula, the defect position shows black due to the fact that the magnetic suspension is sprayed, the average value of RGB three values is closer to 0, therefore, the D value is small, and the RGB three values are different and the D value is large in other areas with bright colors.
In the image model, firstly, the color space is converted from RGB to HSV, where H is expressed as a hue of a pixel, S is expressed as a saturation of a pixel, and V is expressed as a brightness of a pixel. And then uniformly quantizing the color space into 256 colors, namely converting the HSV three-dimensional space into a one-dimensional feature space, wherein the quantized color is as follows:
C＝{ci|i＝0,1,2,...,255}
in the definition of the quantized color, CiThe ith quantization color. Defining the number of colors contained in the image as the richness E of the colors, and the image color richness formula is as follows:
in the color richness formula, the defect position shows black due to the fact that the magnetic suspension is sprayed, the E value of the image is small, other part of pixels are colored, and the E value is large even though the D value is not obvious.
S8, clustering and uploading the preprocessed images based on the MCF-VGG image classification model;
the MCF-VGG image classification model is based on a VGG-19 model, the network model classifies 5 groups and uses a convolution kernel of 3x3, and the model adds Markov random field constraints at the 3 rd layer, the 5 th layer and the 9 th layer to perform spatial local limitation on underwater images. The local similarity of the images is strong after the magnetic suspension is sprayed, so that the extraction of the local detail features of the images is very important.
The markov random field constraint is defined as: is provided with
Is composed of
Taking a feature map set of local blocks, each image block is indexed as
And the size is k multiplied by C, wherein k is the height and width of the block, C is the number of channels of the layer where the block is located, and the potential energy function is set as:
function of potential energyIn, EMRFIn order to be a markov random field constraint,
for from each block
The best matching block is found, using the normalized cross-correlation coefficient at all
M ofrIn the block, the normalized cross-correlation function is obtained as:
in the normalized cross-correlation function, m is
A cardinality of (a);
to be driven from
And taking a feature mapping set of the local block.
In the MCF-VGG image classification model, the defect position is black due to the fact that magnetic suspension is sprayed, the detail features of surrounding image blocks are extracted, and the defect image is classified. If the proportion of the defects in the full image is less than or equal to 3%, the defects are considered to be fine defects and can be marked as hidden defects; if the defect accounts for more than 3% and less than or equal to 20% of the full image, the defect is considered to have a common defect and is marked as a common defect; if the defect accounts for more than 20% in the full image, the existence of the serious welding seam is considered to be marked as the serious welding seam and an alarm is given.
In conclusion, the device and the method provided by the invention realize the integrated operation flow of underwater magnetic powder and visual nondestructive flaw detection, and the MCF-VGG image classification model is adopted to classify the detected damage, so that compared with manual flaw detection, the device and the method have clear quantitative indexes, the influence of the professional level of workers on the damage detection rate is fundamentally solved, and the flaw detection effect of underwater magnetic powder flaw detection is greatly improved.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (6)
1. The processing method of the underwater nondestructive inspection equipment based on the combination of vision and magnetic powder is characterized in that: the underwater nondestructive inspection device comprises an underwater nondestructive inspection device and an underwater movable platform, wherein the underwater nondestructive inspection device is specified in the underwater movable platform; the underwater nondestructive flaw detection device mainly comprises a flaw detector control module, a camera module, a communication module and an image processing module, wherein the flaw detector control module is respectively connected with the camera module, the communication module and the image processing module;
the underwater nondestructive inspection device also comprises a universal joint, a hose, a magnetic suspension spray head and a magnetic powder inspection instrument, wherein the magnetic powder inspection instrument, the hose and the camera module are fixed on the underwater movable platform through the universal joint, the angles of the modules are adjusted by adjusting the universal joint, and the magnetic suspension is sprayed through the hose and the magnetic suspension spray head;
the processing method comprises the following steps:
s1, positioning and adsorbing an underwater nondestructive inspection real-time control system on a pipeline based on a motion control module, and feeding back pose information;
s2, the underwater nondestructive inspection real-time control system inspects the workpiece and sprays magnetic suspension;
s3, the underwater nondestructive inspection real-time control system inspects the workpiece, and acquires and uploads image information with magnetic suspension;
s4, the underwater nondestructive inspection real-time control system inspects the workpiece, and the flaw detector adsorbs magnetic suspension;
s5, an underwater nondestructive inspection real-time control system inspects the workpiece, and acquires and uploads image information after magnetic powder adsorption;
s6, comparing the images before and after adsorption to find out difference points;
s7, marking difference point images based on structural similarity, gray difference and color richness;
s8, clustering and uploading the preprocessed images based on the MCF-VGG image classification model; the MCF-VGG image classification model is based on a VGG-19 model, the image classification model classifies 5 groups and uses a convolution kernel of 3x3, and the image classification model adds Markov random field constraints at a 3 rd layer, a 5 th layer and a 9 th layer to perform spatial local limitation on underwater images.
2. The processing method of underwater nondestructive inspection equipment based on combination of vision and magnetic powder according to claim 1, characterized in that: step S1 specifically includes: the motion control module adjusts the relative adsorption force between the adsorption module and the pipeline to realize the adsorption function, and through the universal wheel and the control of the propeller, the device can move on the pipeline, and the position of the device finally adsorbed on the pipeline is transmitted to the PC through the communication module.
3. The processing method of underwater nondestructive inspection equipment based on combination of vision and magnetic powder according to claim 1, characterized in that: the step S3 is: when the motion control module patrols the pipeline for one week, the camera module records an image of the pipeline for one week, generates a panoramic image of the underwater pipeline after the magnetic suspension liquid is sprayed, and uploads pipeline image information to the PC through the communication module.
4. The processing method of underwater nondestructive inspection equipment based on combination of vision and magnetic powder according to claim 1, characterized in that: the step S6 is: the image information after the magnetic suspension is sprayed and adsorbed is compared, and the damage images are classified through the image processing module.
5. The processing method of underwater nondestructive inspection equipment based on combination of vision and magnetic powder according to claim 1, characterized in that: the step S7 is: based on the image processing module, by comparing the image information before and after the magnetic suspension liquid is sprayed, based on the three characteristics of image structure similarity, gray difference and color richness, the images are pre-classified by considering that the magnetic suspension liquid residue exists at the defect position and is close to black.
6. The processing method of underwater nondestructive inspection equipment based on combination of vision and magnetic powder according to claim 1, characterized in that: the step S8 is: based on the image processing module, the classified images are classified through the MCF-VGG image classification model clustering features, and then the classified images are correspondingly marked.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110261616.4A CN112924466B (en) | 2021-03-10 | 2021-03-10 | Underwater nondestructive inspection equipment based on combination of vision and magnetic powder and processing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110261616.4A CN112924466B (en) | 2021-03-10 | 2021-03-10 | Underwater nondestructive inspection equipment based on combination of vision and magnetic powder and processing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112924466A CN112924466A (en) | 2021-06-08 |
| CN112924466B true CN112924466B (en) | 2021-12-24 |
Family
ID=76172471
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110261616.4A Active CN112924466B (en) | 2021-03-10 | 2021-03-10 | Underwater nondestructive inspection equipment based on combination of vision and magnetic powder and processing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112924466B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114594154A (en) * | 2022-03-02 | 2022-06-07 | 北京工业大学 | Steel structure underwater part intelligent flaw detection robot based on magnetic flux leakage detection technology and detection method |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9239297B2 (en) * | 2012-11-26 | 2016-01-19 | Saudi Arabian Oil Company | Outer surface inspecting robot with flipping over flange mechanism |
| CN211710961U (en) * | 2020-03-14 | 2020-10-20 | 温州大学 | Walking robot for pipeline flaw detection |
| CN111398411A (en) * | 2020-04-28 | 2020-07-10 | 秦皇岛市盛通无损检测有限责任公司 | Magnetic automatic check out system |
| CN212718678U (en) * | 2020-07-10 | 2021-03-16 | 南通理工学院 | Pipeline overhauls device based on underwater robot |
-
2021
- 2021-03-10 CN CN202110261616.4A patent/CN112924466B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112924466A (en) | 2021-06-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112884760B (en) | Intelligent detection method for multi-type diseases of near-water bridge and unmanned ship equipment | |
| CN115439424B (en) | Intelligent detection method for aerial video images of unmanned aerial vehicle | |
| CN112067839B (en) | Method for quickly measuring surface flow field of ultra-wide river of unmanned aerial vehicle | |
| KR101796258B1 (en) | A construction safety inspection method based on vision using small unmanned aerial vehicles | |
| CN112924466B (en) | Underwater nondestructive inspection equipment based on combination of vision and magnetic powder and processing method | |
| Dufek et al. | Visual pose estimation of USV from UAV to assist drowning victims recovery | |
| US20240013505A1 (en) | Method, system, medium, equipment and terminal for inland vessel identification and depth estimation for smart maritime | |
| CN111709994B (en) | Autonomous unmanned aerial vehicle visual detection and guidance system and method | |
| CN109117838B (en) | Target detection method and device applied to unmanned ship sensing system | |
| CN108871409A (en) | A kind of fault detection method and system | |
| CN113763562A (en) | Binocular vision-based facade feature detection and facade feature processing method | |
| CN113538503A (en) | Solar panel defect detection method based on infrared image | |
| CN112102395A (en) | Autonomous inspection method based on machine vision | |
| CN110136104B (en) | Image processing method, system and medium based on unmanned aerial vehicle ground station | |
| CN116309851B (en) | Position and orientation calibration method for intelligent park monitoring camera | |
| Bonnin-Pascual et al. | A flying tool for sensing vessel structure defects using image contrast-based saliency | |
| CN112115737B (en) | Vehicle orientation determining method and device and vehicle-mounted terminal | |
| CN111798516A (en) | Method for detecting running state quantity of bridge crane equipment and analyzing errors | |
| CN212861692U (en) | Butt joint device of unmanned aerial vehicle suspension type load unmanned trolley | |
| CN114119485A (en) | Mixed vision slope detection method | |
| CN112528982A (en) | Method, device and system for detecting water gauge line of ship | |
| Kim et al. | Application of image quality assessment for rockfall investigation | |
| CN112036393A (en) | Identification method based on shale gas field production single-pointer meter reading | |
| KR102586491B1 (en) | Unmanned underwater inspection robot device | |
| CN109342439A (en) | Cable Structure appearance detecting method based on unmanned plane |
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 | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20210608 Assignee: NANTONG ZHONGNENG MACHINERY Co.,Ltd. Assignor: NANTONG University Contract record no.: X2023980053318 Denomination of invention: Underwater non-destructive testing equipment and processing method based on the combination of vision and magnetic powder Granted publication date: 20211224 License type: Common License Record date: 20231221 |