CN113295732B - Pipeline robot capable of detecting pipeline defects and control method and control system thereof - Google Patents
Pipeline robot capable of detecting pipeline defects and control method and control system thereof Download PDFInfo
- Publication number
- CN113295732B CN113295732B CN202110435345.XA CN202110435345A CN113295732B CN 113295732 B CN113295732 B CN 113295732B CN 202110435345 A CN202110435345 A CN 202110435345A CN 113295732 B CN113295732 B CN 113295732B
- Authority
- CN
- China
- Prior art keywords
- pipeline
- data
- matrix
- thermal image
- processor
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 16
- 239000011159 matrix material Substances 0.000 claims abstract description 65
- 238000010438 heat treatment Methods 0.000 claims abstract description 12
- 230000002087 whitening effect Effects 0.000 claims abstract description 12
- 238000010191 image analysis Methods 0.000 claims abstract description 8
- 238000010606 normalization Methods 0.000 claims abstract description 5
- 238000000926 separation method Methods 0.000 claims description 13
- 238000001514 detection method Methods 0.000 claims description 5
- 230000007847 structural defect Effects 0.000 abstract description 9
- 238000006386 neutralization reaction Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 3
- 239000012530 fluid Substances 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N25/00—Investigating or analyzing materials by the use of thermal means
- G01N25/72—Investigating presence of flaws
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05B—ELECTRIC HEATING; ELECTRIC LIGHT SOURCES NOT OTHERWISE PROVIDED FOR; CIRCUIT ARRANGEMENTS FOR ELECTRIC LIGHT SOURCES, IN GENERAL
- H05B3/00—Ohmic-resistance heating
- H05B3/0033—Heating devices using lamps
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Manipulator (AREA)
Abstract
The invention provides a pipeline robot capable of detecting pipeline defects, a control method and a control system thereof, which are mainly characterized in that a pipeline robot body is arranged in a pipeline, the pipeline is subjected to pulse heating through a flash lamp, meanwhile, a thermal imager is matched for thermal image acquisition, after acquisition, each thermal image acquisition data is made into two-dimensional thermal image matrix data, then the operations of neutralization, whitening, Gaussian operation, orthogonalization, normalization and the like are sequentially carried out, finally, an independent component matrix is obtained, each internal independent component is rearranged to obtain thermal image analysis data, and therefore, the part of the pipeline with the structural defects can be clearly shown.
Description
Technical Field
The invention relates to the technical field of robots, in particular to a pipeline robot capable of detecting pipeline defects and a control method and a control system thereof.
Background
At present to the detection of pipeline, maintenance, or state exploration in the pipeline, perhaps clear up the interior siltation of pipeline again, mostly adopt pipeline robot to accomplish. The detection of the pipeline is mostly done by relying on image recognition. However, image recognition can only recognize defects on the inner wall surface of the pipe, and defects on the pipe structure are difficult to recognize, and therefore, the present inventors considered that such problems need to be solved, and began to think about solutions.
Disclosure of Invention
The invention solves the problem that the pipeline robot can only judge the defects on the surface of the pipeline when identifying the defects of the pipeline, and the structural defects are difficult to identify.
In order to solve the above problems, the present invention provides a pipeline robot for detecting pipeline defects, a control method and a control system thereof, wherein the technical scheme is as follows:
the pipeline robot body is arranged in a pipeline and can be moved in the pipeline in a preset route or a remote control mode and the like, when the pipeline robot body is to detect the defects of the pipeline, a flash lamp is mainly used for conducting pulse heating on the pipeline for about 0.2 second in 2000W, and when the pulse heating is conducted, the thermal imager is used for conducting pulse heating on the pipeline with 30 frames/secondAcquiring a plurality of thermal image acquisition data, integrating each thermal image acquisition data into a two-dimensional thermal image matrix data n by a processor x n y Then, the two-dimensional thermal image matrix data is subjected to a series of operations to obtain an orthogonal separation matrix, then the orthogonal separation matrix is used for calculating an independent component matrix, and finally the processor rearranges each independent component in the independent component matrix into n x *n y In this way, a plurality of thermal image analysis data can be obtained.
Therefore, whether the pipeline has structural defects can be clearly shown through the thermal image analysis data, and if the pipeline has structural defects, corresponding measures such as remedy, prevention and the like can be carried out in advance to maintain the safety of the pipeline.
Drawings
FIG. 1 is a schematic view of an embodiment of the present invention shown in FIG. 1;
FIG. 2 is a schematic view of an embodiment of the present invention FIG. 2;
FIG. 3 is a schematic view of an embodiment of the present invention shown in FIG. 3;
FIG. 4 is a schematic view of the linkage of the components of the present invention;
FIG. 5 is a schematic diagram of the thermal test results of the present invention;
FIG. 6 is a flow chart of the present invention;
FIG. 7 is a schematic diagram of three-dimensional thermal image matrix data according to the present invention;
FIG. 8 is a schematic diagram of two-dimensional thermal image matrix data according to the present invention.
Description of reference numerals:
a-a pipeline; b1-plate body; b2-structural defects; 1-a pipeline robot body; 11-a tip; 2-a flash lamp; 3-a thermal imager; 4-a processor; 5-a positioning unit; 6-a power wheel set; 7-a tilting unit; 8, telescopic rods; 9-inclination angle identification unit.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
Referring to fig. 4, the present invention includes a pipe robot body 1, a flash lamp 2, a thermal imager 3, a processor 4, a positioning unit 5, a power wheel set 6, an inclined unit 7, an expansion link 8, and an inclination angle detecting unit 9. Wherein, flash light 2 reach thermal imager 3 set up in the pipeline robot body 1 outside, in the bottom of pipeline robot body 1 is equipped with power wheelset 6, in the top surface of pipeline robot body 1 then sets up according to the preface from bottom to top slope unit 7 reaches telescopic link 8, positioning unit 5 reaches processor 4 then locates inside the pipeline robot body 1. Referring to fig. 1 to 3, the front side of the pipe robot body 1 is gradually tapered from the left half and the right half toward the center to form a tip 11, and the resistance of the fluid can be reduced through the tip 11, so that when there is fluid in the pipe a, the resistance to advance can be reduced, and the impact of the fluid on the pipe robot body 1 can be reduced.
Referring to fig. 1 to 3, the pipeline robot body 1 can be operated in the pipeline a through a preset moving route or by using a remote control method, so that the pipeline robot body 1 moves in the pipeline a. When pipeline robot body 1 need carry out the hot image and pick up, permeable control the elongation of telescopic link 8 makes 8 one end of telescopic link withstands pipeline A's roof, makes pipeline robot body 1 is fixed in the pipeline A, in order to avoid pipeline robot body 1 receives external force to influence and produces and rock, and then influences the effect of whole hot image capture. In addition, when the pipeline robot body 1 moves to the inclined plane and needs to capture the thermal image, in order to make the pipeline robot body 1 have a better fixing effect, the inclination unit 7 can adjust the inclination angle according to the detection result of the inclination angle detection unit 9, so that the telescopic rod 8 can keep vertically and upwards propping against the top wall of the pipeline a, so that the pipeline robot body 1 can be stabilized in the pipeline a.
Referring to fig. 4 and 6, when detecting whether the pipeline a has a structural defect, the flash lamp 2 is first controlled to perform pulse heating on the pipeline a, and the pulse heating processPulse heating is carried out for about 0.2 second at 2000W to carry out pulse heating on the pipeline A, and the thermal imager 3 is utilized to carry out thermal image acquisition on the pipeline A while the pulse heating is carried out, so that a plurality of thermal image acquisition data n are obtained t Referring to FIG. 7, each thermal image capture data includes a plurality of horizontal pixel data n x And a plurality of vertical pixel data n y Then, the processor 4 will make each thermal image capturing data into a three-dimensional thermal image matrix data n t *n x *n y Then, referring to fig. 8, the processor 4 converts the three-dimensional thermal image matrix data into two-dimensional thermal image matrix data n based on the three-dimensional thermal image matrix data t *n x n y Wherein n is x n y Representing the number of variables.
In order to speed up the whole instruction cycle, the complexity of the whole operation needs to be reduced to reduce the operation amount, so the two hot image matrix data needs to be processed with operation procedures such as neutralization and whitening. Firstly, the neutralization is that the processor 4 firstly calculates an average value according to each variable quantity of the two-dimensional thermal image matrix data, and then subtracts the average value from each variable quantity of the two-dimensional thermal image matrix data to obtain a neutralization matrix
Then, the whitening operation is performed, in which the processor 4 sequentially uses the centering matrices according to the formula:
C x ＝EDE T 、M＝ED -1/2 E T 、
performing operation to obtain a whitening matrix Z, wherein E represents an unit orthogonal matrix, M represents a whitening matrix, Z represents a whitening matrix, D represents a diagonal matrix, and C x Representing a co-variance matrix.
Then, the non-Gaussian calculation is performed by adopting a negative entropy mode, and the processor 4 firstly selects a quadratic highThe function is G (y) ═ y 4 The overall operation is simple without additional parameter selection, and then the random vector b is selected i And b i 1, and according to the formula: b i ＝E{Zg(b i T Z)}-E{Zg'(b i T Z)}b i Performing iterative operation from i to 1 until i to m to obtain a complex random vector; wherein m is the number of the thermal image capturing data, G (y) is a non-quadratic Gaussian function, y is a probability variable, g is a first order differential of G (y), and g' is a second order differential of G (y).
After each random vector is calculated, the processor 4 performs a process of orthogonalizing and normalizing each random vector, in which the processor 4 firstly performs the following steps according to the formula:
performing an orthogonalization operation according to the following formula:
performing normalization operation, wherein the orthogonalization and normalization operation is performed in the process of starting from i to 1 until i to m, and if b is i Form a convergent output b i Finally, each b is i Defined as an orthogonal separation matrix B.
After the orthogonal separation matrix is obtained after the operation, the part of the data belonging to the independent component is separated through the orthogonal separation matrix, and the processor 4 is respectively according to the formula:
and the formula: w is B T M, calculating a separation matrix W and independent component matrix
Rearranging each independent component in the independent component matrix into n x *n y Then, a thermal image analysis data is obtained.
As shown in fig. 5, the board C1 and the default structural defect C2 are on the left, and the defect part in the thermal image analysis data can be clearly highlighted by the present invention.
Since the number of thermal image analysis data generated through the above steps is too large, it is quite difficult for the manager to quickly find whether a structural defect occurs in the pipeline a, and in order to increase the inspection speed, the processor 4 may further calculate the following formula: k ═ E { y 4 }-3(E{y 2 }) 2 Calculating peak value k of each independent component, taking the highest and the second highest values from each peak value as the highest peak value and the second highest value, calculating an average peak value according to each peak value, when the difference value between the highest peak value and the average peak value exceeds a default value, indicating that the pipeline A generates structural defects, then taking out the independent components corresponding to the highest peak value and the second highest value, and rearranging the independent components into n x *n y And a defect data is obtained, as shown in fig. 5, the defect data obviously presents a defect part, so that the relevant management personnel can rapidly take measures such as remedy, emergency repair and the like.
In order to allow the relevant management personnel to dispatch to quickly go to process when the pipeline a detects the structural defect, the defect data preferably includes positioning data, and the positioning data is obtained by using the positioning unit 5 to detect the position of the pipeline robot body 1.
Although the present disclosure has been described above, the scope of the present disclosure is not limited thereto. Various changes and modifications may be effected therein by one of ordinary skill in the pertinent art without departing from the spirit and scope of the present disclosure, and these changes and modifications are intended to be within the scope of the present disclosure.
Claims (9)
1. Can supply to detect pipeline robot of pipeline defect, its characterized in that includes:
the system comprises a pipeline robot body, a flash lamp, a thermal imager and a processor; wherein,
the pipeline robot body is provided with the flash lamp and the thermal imager;
the flash lamp can be used for pulse heating of the pipeline;
the thermal imager is used for capturing thermal images of the pipeline while the pipeline is heated by the pulse to obtain a plurality of thermal image capturing data, wherein each thermal image capturing data respectively comprises a plurality of horizontal pixel data and a plurality of vertical pixel data;
the processor makes the plurality of thermal image acquisition data into three-dimensional thermal image matrix data n t *n x *n y Wherein n is t Representing the thermal image capture data, n x Representing said horizontal pixel data, n y Representing the vertical pixel data; then converting the three-dimensional thermal image matrix data into two-dimensional thermal image matrix data n t *n x n y Wherein n is x n y Represents the number of variables; and (c) a second step of,
the processor centralizes the two-dimensional thermal image matrix data, the processor calculates an average value according to each variable quantity of the two-dimensional thermal image matrix data, and then subtracts the average value from each variable quantity to obtain a centralized matrix
Then according to the formula:
C x ＝EDE T 、M＝ED -1/2 E T 、
obtaining a whitening matrix Z, wherein E represents an unit orthogonal matrix, M represents a whitening matrix, Z represents a whitening matrix, D represents a diagonal matrix, C x Represents a common variation matrix;
the processor selects a random vector b i And b i 1, and according to the formula: b i ＝E{Zg(b i T Z)}-E{Zg'(b i T Z)}b i And g (y) ═ y 4 Starting from i-1, the iteration is carried outCarrying out generation operation until i is m to obtain a complex random vector; wherein m is the number of the thermal image capturing data, G (y) is a non-quadratic Gaussian function, y is a probability variable, g is a first order differential of G (y), and g' is a second order differential of G (y);
the processor then, according to the formula:
and the formula:
the orthogonalization and normalization operations are sequentially performed from i equal to 1 until i equal to m, and if b is i Form a convergent output b i Finally, each b is i Defining an orthogonal separation matrix B;
the processor respectively converts the orthogonal separation matrix into a plurality of orthogonal separation matrices according to the formula:
and the formula: w is B T M, calculating a separation matrix W and independent component matrix
Rearranging each independent component in the independent component matrix into n x *n y Then, a thermal image analysis data is obtained.
2. The pipeline robot for detecting pipeline defects according to claim 1, wherein each independent component in the independent component matrix is determined according to the formula: k ═ E { y 4 }-3(E{y 2 }) 2 Calculating peak value k of each independent component, taking the highest and the second highest values from each peak value as the highest peak value and the second highest value, calculating an average peak value according to each peak value, taking out the independent components corresponding to the highest peak value and the second highest value when the difference value between the highest peak value and the average peak value exceeds a default value, and rearranging the independent components into n x *n y To obtain aAnd defect data.
3. The pipeline robot for detecting the pipeline defects as claimed in claim 2, wherein a positioning unit is provided inside the pipeline robot body, and the positioning unit is used for detecting the position of the pipeline robot body to obtain positioning data; when the processor calculates the defect data, the processor stores the positioning data in the defect data.
4. The pipeline robot for detecting the pipeline defect as claimed in claim 3, wherein a power wheel set is provided at the bottom of the pipeline robot body for driving the pipeline robot body to travel; the top surface of the pipeline robot body is sequentially provided with an inclined unit and a telescopic rod from bottom to top; the pipeline robot body is internally provided with an inclination angle detecting unit, the processor is in information connection with the inclination angle detecting unit and the telescopic rod, the processor can be used for controlling the inclination unit according to the detecting result of the inclination angle detecting unit, and the processor can be used for controlling the elongation of the telescopic rod.
5. A control method of a pipeline robot for detecting a defect of a pipeline, which is applied to the pipeline robot of any one of claims 1 to 4, the pipeline robot comprising: the system comprises a pipeline robot body, a flash lamp, a thermal imager and a processor; the control method comprises the following steps:
(A) the pipeline robot body is arranged in the pipeline, and the pipeline is subjected to pulse heating by using the flash lamp; controlling the thermal imager to work while the pulse heating is carried out so as to carry out thermal image acquisition on the pipeline to obtain a plurality of thermal image acquisition data, wherein each thermal image acquisition data respectively comprises a plurality of horizontal pixel data and a plurality of vertical pixel data;
(B) the processor makes the plurality of thermal image acquisition data into three-dimensional thermal image matrix data n t *n x *n y Wherein n is t Representing the thermal image capture data, n x Representing said horizontal pixel data, n y Representing the vertical pixel data; then converting the three-dimensional thermal image matrix data into two-dimensional thermal image matrix data n t *n x n y Wherein n is x n y Represents the number of variables;
(C) the processor centralizes the two-dimensional thermal image matrix data, the processor calculates an average value according to each variable quantity of the two-dimensional thermal image matrix data, and then subtracts the average value from each variable quantity to obtain a centralized matrix
The processor then sequentially according to a formula:
C x ＝EDE T 、M＝ED -1/2 E T 、
obtaining a whitening matrix Z, wherein E represents an unit orthogonal matrix, M represents a whitening matrix, Z represents a whitening matrix, D represents a diagonal matrix, C x Represents a common variation matrix;
(D) the processor selects a random vector b i And b i 1, according to the formula: b i ＝E{Zg(b i T Z)}-E{Zg'(b i T Z)}b i And g (y) ═ y 4 Performing iterative operation from i to 1 until i to m to obtain a complex random vector; wherein m is the number of the thermal image capturing data, G (y) is a non-quadratic Gaussian function, y is a probability variable, g is a first order differential of G (y), and g' is a second order differential of G (y);
(E) the processor is configured to, according to the formula:
and the formula:
the orthogonalization and normalization operations are sequentially performed from i equal to 1 until i equal to m, and if b is i Form a convergent output b i Finally, each b is i Defining an orthogonal separation matrix B;
(F) the processor respectively uses the orthogonal separation matrixes to:
and the formula: w is B T M, calculating a separation matrix W and independent component matrix
Rearranging each independent component in the independent component matrix into n x *n y Then, a thermal image analysis data is obtained.
6. The method for controlling a pipeline robot capable of detecting a pipeline defect according to claim 5, further comprising the step (G): the processor compares each independent component in the independent component matrix according to a formula: k ═ E { y 4 }-3(E{y 2 }) 2 Calculating peak value k of each independent component, taking the highest and the second highest values from each peak value as the highest peak value and the second highest value, calculating an average peak value according to each peak value, and taking out the independent components corresponding to the highest peak value and the second highest value by the processor when the difference value between the highest peak value and the average peak value exceeds a default value and rearranging the independent components into n x *n y Thereby obtaining a defect data.
7. The method for controlling a pipeline robot capable of detecting a pipeline defect according to claim 6, further comprising the step (H): when the defect data is calculated, the processor controls the positioning unit of the pipeline robot body to work so as to detect the position of the pipeline robot body to obtain positioning data, and the positioning data is stored in the defect data.
8. The method for controlling a pipeline robot capable of detecting pipeline defects according to claim 7, further comprising the step (I): when the inclination angle detecting unit of the pipeline robot body detects that the pipeline robot body is in an inclined state, the processor controls the inclination unit of the pipeline robot body to change the inclination angle according to the detection result of the inclination angle detecting unit.
9. Robot control system, its characterized in that includes:
the pipeline robot of any one of the preceding claims 1-4;
a control center, wherein the control center is connected to the pipeline robot in an information mode;
the control center controls the pipeline robot according to the control method of any one of the above claims 5 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110435345.XA CN113295732B (en) | 2021-04-22 | 2021-04-22 | Pipeline robot capable of detecting pipeline defects and control method and control system thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110435345.XA CN113295732B (en) | 2021-04-22 | 2021-04-22 | Pipeline robot capable of detecting pipeline defects and control method and control system thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113295732A CN113295732A (en) | 2021-08-24 |
| CN113295732B true CN113295732B (en) | 2022-09-30 |
Family
ID=77320044
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110435345.XA Active CN113295732B (en) | 2021-04-22 | 2021-04-22 | Pipeline robot capable of detecting pipeline defects and control method and control system thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113295732B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103592333A (en) * | 2013-11-13 | 2014-02-19 | 电子科技大学 | Automatic defect detection and identification method for ECPT (eddy current pulsed thermography) |
Family Cites Families (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7220966B2 (en) * | 2003-07-29 | 2007-05-22 | Toyota Motor Manufacturing North America, Inc. | Systems and methods for inspecting coatings, surfaces and interfaces |
| CN102692429B (en) * | 2011-03-24 | 2013-10-30 | 中国科学院沈阳自动化研究所 | Method for automatic identification and detection of defect in composite material |
| CN103761996B (en) * | 2013-10-18 | 2016-03-02 | 中广核检测技术有限公司 | Based on the Non-Destructive Testing intelligent robot detection method of virtual reality technology |
| DE102014218136B4 (en) * | 2014-09-10 | 2019-07-18 | Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. | Thermographic examination device and method for the non-destructive examination of a near-surface structure on a test object |
| CN104698036B (en) * | 2015-04-01 | 2017-12-05 | 武汉理工大学 | Vortex thermal imaging imperfection recognition methods based on three dimensional temperature curved surface similarity analysis |
| US10546207B2 (en) * | 2016-04-11 | 2020-01-28 | North Carolina Agricultural And Technical State University | Normalized defect characterization of pulse thermographic nondestructive evaluation |
| US10564108B2 (en) * | 2017-07-03 | 2020-02-18 | Saudi Arabian Oil Company | Apparatus and method for nondestructively inspecting fiberglass and nonmetallic pipes |
| CN108195884A (en) * | 2018-01-12 | 2018-06-22 | 西南科技大学 | A kind of lossless detection method and system based on current vortex pulse thermal imaging |
| CN108665442A (en) * | 2018-04-03 | 2018-10-16 | 中国空气动力研究与发展中心超高速空气动力研究所 | The thermal image defect characteristic of Infrared Non-destructive Testing enhances processing method |
| CN108717069B (en) * | 2018-05-29 | 2020-08-11 | 电子科技大学 | High-pressure container thermal imaging defect detection method based on line variable step length segmentation |
| CN109926341A (en) * | 2019-03-26 | 2019-06-25 | 武汉大学 | Silicon photrouics scanning vortex thermal imaging detection platform and defect classification method |
| CN110335204B (en) * | 2019-05-07 | 2021-06-01 | 中国人民解放军陆军工程大学 | Thermal imaging image enhancement method |
| CN111598887B (en) * | 2020-05-25 | 2023-04-07 | 中国空气动力研究与发展中心超高速空气动力研究所 | Spacecraft defect detection method based on LVQ-GMM algorithm and multi-objective optimization segmentation algorithm |
| CN112215830B (en) * | 2020-10-21 | 2022-03-04 | 中国空气动力研究与发展中心超高速空气动力研究所 | Method for judging impact damage characteristic types of aerospace heat-proof materials |
| CN112461892B (en) * | 2020-11-02 | 2022-07-22 | 浙江工业大学 | Infrared thermal image analysis method for nondestructive detection of composite material defects |
| CN112461893B (en) * | 2020-11-05 | 2022-11-22 | 宁波晶成机械制造有限公司 | Nondestructive testing device and method based on thermal imaging principle |
| CN112489016B (en) * | 2020-11-30 | 2024-02-20 | 浙江工业大学 | Local sensitivity discriminant analysis method for composite material defect thermal image graph |
-
2021
- 2021-04-22 CN CN202110435345.XA patent/CN113295732B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103592333A (en) * | 2013-11-13 | 2014-02-19 | 电子科技大学 | Automatic defect detection and identification method for ECPT (eddy current pulsed thermography) |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113295732A (en) | 2021-08-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109102522B (en) | Target tracking method and device | |
| CN111712853B (en) | Processing method and processing device using same | |
| CN108564065B (en) | Cable tunnel open fire identification method based on SSD | |
| CN110490866B (en) | Metal additive forming size real-time prediction method based on depth feature fusion | |
| CN112906797A (en) | Plane grabbing detection method based on computer vision and deep learning | |
| CN109085113A (en) | A kind of Atomatic focusing method and device for cervical exfoliated cell detection device | |
| CN113033547B (en) | MobileNetV 2-based welding state classification method | |
| JP6651702B2 (en) | Object detection device, object detection method, and information processing program | |
| CN113295732B (en) | Pipeline robot capable of detecting pipeline defects and control method and control system thereof | |
| CN112967388A (en) | Training method and device for three-dimensional time sequence image neural network model | |
| CN112801892A (en) | FFWA-based self-adaptive Canny aircraft skin infrared image edge detection method | |
| WO2020209046A1 (en) | Object detection device | |
| KR101779040B1 (en) | Method and apparatus for extracting panel area from thermal infrared images of photovoltaic array | |
| CN110598665B (en) | Pole number identification method based on vehicle-mounted mobile deep learning platform | |
| CN113870174A (en) | Ultraviolet image corona identification positioning method and system based on image fusion | |
| JP6760656B2 (en) | Object identification method | |
| CN106381264A (en) | Wide-range automatic positioning method of robot assisted microinjection system medium trace pipette needle point | |
| JP4935769B2 (en) | Plane region estimation apparatus and program | |
| US12094227B2 (en) | Object recognition device and object recognition method | |
| KR101236845B1 (en) | System for measuring an object and method for measuring an object using the same | |
| CN116475563A (en) | Deep learning three-dimensional weld tracking method and device | |
| Rashd et al. | Open-box target for extrinsic calibration of LiDAR, camera and industrial robot | |
| KR101391668B1 (en) | System of recognizing obstacle and, method of recognizing obstacle on 4 bundle power transmisson line | |
| CN115330751A (en) | Bolt detection and positioning method based on YOLOv5 and Realsense | |
| JP6852406B2 (en) | Distance measuring device, distance measuring method and distance measuring program |
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 |