CN110057745A - A kind of infrared detection method of metal component corrosion condition - Google Patents
A kind of infrared detection method of metal component corrosion condition Download PDFInfo
- Publication number
- CN110057745A CN110057745A CN201910316762.5A CN201910316762A CN110057745A CN 110057745 A CN110057745 A CN 110057745A CN 201910316762 A CN201910316762 A CN 201910316762A CN 110057745 A CN110057745 A CN 110057745A
- Authority
- CN
- China
- Prior art keywords
- corrosion
- temperature
- metal component
- area
- infrared
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N17/00—Investigating resistance of materials to the weather, to corrosion, or to light
- G01N17/006—Investigating resistance of materials to the weather, to corrosion, or to light of metals
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Ecology (AREA)
- Environmental & Geological Engineering (AREA)
- Environmental Sciences (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
- Radiation Pyrometers (AREA)
Abstract
The invention belongs to infrared thermography non-destructive evaluation technical fields, and specifically disclose a kind of infrared detection method of metal component corrosion condition.This method includes obtaining the infrared image of metal component and carrying out filtering and noise reduction processing, and then given threshold obtains binary image；Indicia etched region and non-corrosion area, and draw the profile of corrosion area；According to the mask of corrosion area in the contours extract binary image of corrosion area, the temperature of corrosion area is calculated in infrared image using the mask；By the temperature input temp corrosion depth transformation model of corrosion area, the corrosion depth of metal component is obtained.The infrared detection method of metal component corrosion condition provided by the invention, infrared image need to only be handled, and the corrosion condition of metal component can be specifically described in terms of three according to temperature corrosion depth transformation model, including corrosion sites, corroded area and corrosion depth, qualitative and quantitative analysis is carried out to the corrosion condition of metal component to realize.
Description
Technical field
The invention belongs to infrared thermography non-destructive evaluation technical fields, more particularly, to a kind of metal component corrosion condition
Infrared detection method.
Background technique
Corrosion is the chemistry or electrochemical reaction between metal or metal alloy and its environment, leads to material and its performance
Deterioration.If handled without discovery in time, corrosion will lead to serious metal failure, and may cause economy and secure context
It influences.
Infrared Non-destructive Testing technology is a kind of ideal non-destructive testing technology of effect, and principle is by heat source to be detected
Test specimen is heated, using the real-time image signal of infrared thermal imaging equipment acquisition surface of test piece temperature.In heat transfer process,
When corroding inside test specimen, the heat-conductive characteristic of material can change, and the surface temperature of test specimen generates uneven distribution, pass through
Handle the temperature signal of acquisition, it can be determined that the corrosion information inside test specimen.
Infrared Non-destructive Testing technology has been widely used for electronics industry, machine-building, pipe detection and aviation boat at present
The industries such as it, but be mainly limited to determine corrosion sites in practical application, the quantitative analysis of corrosion condition is also lacked
Strong theoretical foundation.Although the numerical simulation analysis for extent of corrosion more existing at present is theoretical, still in preliminary
Developing stage, and since it is calculated, complicated, programing work amount is big, is still difficult to provide specific metal component corrosion condition
Image processing algorithm.
Summary of the invention
For the disadvantages mentioned above and/or Improvement requirement of the prior art, the present invention provides a kind of metal component corrosion conditions
Infrared detection method mutually should be able to be according to corrosion area on infrared image wherein by temperature corrosion depth transformation model
Temperature obtains the corrosion depth of metal component, is therefore particularly suitable for the application of detection metal component corrosion condition etc.
To achieve the above object, the invention proposes a kind of infrared detection method of metal component corrosion condition, this method
Include the following steps:
S1 obtains the infrared image of metal component and carries out filtering and noise reduction processing, and then given threshold obtains the infrared figure
The binary image of picture；
S2 indicia etched region and does not corrode according to the connectivity of pixel pixel adjacent thereto each in the binary image
Region, and draw the profile of the corrosion area；
The mask of S3 corrosion area in the binary image according to the contours extract of the corrosion area, uses the mask
The temperature of the corrosion area is calculated in the infrared image；
The temperature input temp corrosion depth transformation model of the corrosion area is obtained the corrosion of the metal component by S4
Depth.
As it is further preferred that in step sl, being filtered denoising using the method that edge retains filtering.
As it is further preferred that in step sl, being obtained using Otsu Binarization methods or maximum normalization temperature differential method
The binary image of the infrared image.
As it is further preferred that in step s3, the temperature of the corrosion area includes each picture in the corrosion area
The maximum temperature of the temperature of vegetarian refreshments, the mean temperature of the corrosion area or the corrosion area.
As it is further preferred that in step s 4, corrosion depth is implicit in the temperature corrosion depth transformation model
Function are as follows:
In formula, AkFor k-th of coefficient of Fourier expansion, βkFor k-th of characteristic value, BkFor k-th of system of Fourier expansion
Number, γkIt is the function about corrosion depth for k-th of characteristic value, τ is heating time, a1For the thermal diffusivity of corrosion layer, a2
For the thermal diffusivity of non-corrosion layer, δ is the thickness of metal component, t0For the initial temperature of metal component, tfFor heating temperature, λ1
For the metallic thermal conductivity of corrosion layer, λ2For the metallic thermal conductivity of non-corrosion layer, h is the surface coefficient of heat transfer of metal component, TbFor not
The temperature of corrosion area, T1For the temperature of corrosion area.
As it is further preferred that in step s 4, the construction method of the temperature corrosion depth transformation model includes such as
Lower sub-step:
S41 constructs the model of non-corrosion area, obtains the temperature T of non-corrosion areabAre as follows:
S42 constructs the model for the corrosion area that corrosion depth is Dep, obtains the temperature T of the corrosion area1Are as follows:
S43 obtains the Implicitly function of corrosion depth Dep according to formula (two) and formula (three) are as follows:
As it is further preferred that further including calculating the corrosion according to the profile of the corrosion area in step s 2
The area in region.
In general, through the invention it is contemplated above technical scheme is compared with the prior art, mainly have below
Technological merit:
1. the present invention combines various technologies such as infrared imaging, signal detection and image procossing, a kind of metal is provided
The infrared detection method of corrosion of component situation, wherein being converted by handling infrared image, and according to temperature corrosion depth
Model can obtain the corrosion sites and corrosion depth of metal component, to accomplish to carry out corrosion qualitative and quantitative point
Analysis can substantially meet the needs of actual production detection, and have lossless, quick, intuitive, non-contact, one-time detection area
Greatly, implement the advantages that simple, be suitable for outfield, on-line checking；
2. especially, the present invention by select input temp for the temperature of pixel each in corrosion area, mean temperature or
Maximum temperature can obtain the corrosion depth of each point, average corrosion depth or maximum corrosion depth in corrosion area, to guarantee
The comprehensive and diversity for obtaining data, and is easily achieved in program, have the advantages that calculating speed fastly, visual result,
One accurately reference can be provided for Corrosion monitoring personnel；
3. simultaneously, the present invention can also calculate the area of corrosion area by the profile of corrosion area, obtain more related
The information of metal component corrosion condition.
Detailed description of the invention
Fig. 1 is the flow chart of the infrared detection method of metal component corrosion condition provided by the invention；
Fig. 2 is the conduction model figure of non-corrosion area when constructing temperature corrosion depth transformation model；
Fig. 3 is the conduction model figure of corrosion area when constructing temperature corrosion depth transformation model；
Fig. 4 is the metal component corrosion condition infrared detection system for obtaining infrared image in the preferred embodiment of the present invention and using
System.
In all the appended drawings, identical appended drawing reference is used to denote the same element or structure, in which:
1- computer analytical equipment, 2- infrared thermal imaging equipment, 3- blast heater, 4- metal component.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.As long as in addition, technical characteristic involved in the various embodiments of the present invention described below
Not constituting a conflict with each other can be combined with each other.
As shown in Figure 1, this method includes such as the present invention provides a kind of infrared detection method of metal component corrosion condition
Lower step:
S1 obtains the infrared image of metal component, and is filtered denoising using the method that edge retains filtering, so
Given threshold obtains the binary image of infrared image afterwards；
S2 is according to the connectivity of pixel pixel adjacent thereto each in binary image, indicia etched region and non-corrosion region
Domain, and the profile of corrosion area is drawn, the area of corrosion area is calculated by the pixel in profile；
S3 is according to the mask of corrosion area in the contours extract binary image of corrosion area, using the mask in infrared figure
The temperature of corrosion area is calculated as in；
Implicitly function of the S4 using corrosion depth Dep in temperature corrosion depth transformation model shown in formula (1), input corrosion
The temperature in region obtains the corrosion depth of metal component；
In formula, Dep is corrosion depth, AkFor k-th of coefficient of Fourier expansion, βkFor k-th of characteristic value, BkFor in Fu
K-th of coefficient of leaf expansion, γkIt is the function about corrosion depth Dep for k-th of characteristic value, τ is heating time, a1For
The thermal diffusivity of corrosion layer, a2For the thermal diffusivity of non-corrosion layer, δ is the thickness of metal component, t0For the initial temperature of metal component
Degree, tfFor heating temperature, λ1For the metallic thermal conductivity of corrosion layer, λ2For the metallic thermal conductivity of non-corrosion layer, h is metal component
Surface coefficient of heat transfer, TbFor the temperature of non-corrosion area, T1For the temperature of corrosion area.
Further, in step sl, infrared image is obtained using Otsu Binarization methods or maximum normalization temperature differential method
Binary image is denoised first using Gaussian kernel according to the size of infrared image when wherein using Otsu Binarization methods, then made
With Otsu Binarization methods；
The detailed process of maximum normalization temperature differential method are as follows:
It is corrosion area by target area marker, if Δ that threshold value of the Δ T ' to judge whether corrosion, which is set, if Δ T ' > 0
Target area marker is then non-corrosion area by T '=0；
In formula, T is the mean temperature of target area, TMFor the maximum temperature of target area, TmFor the lowest temperature of target area
Degree, TbFor the mean temperature of non-corrosion area, TbMFor the maximum temperature of non-corrosion area, TbmFor the lowest temperature of non-corrosion area
Degree.
Further, in step s3, the temperature that the corrosion area is obtained according to the pixel value of corrosion area, by corrosion area
Average pixel value and non-corrosion area average pixel value make it is poor, the gained color difference the big, corrode it is more serious, corrosion area
Temperature includes the maximum temperature of the temperature of each pixel, the mean temperature of corrosion area and corrosion area in corrosion area.
Further, in step s 4, the method for constructing temperature corrosion depth transformation model includes following sub-step:
S41 to simplify the calculation, only considers that metal component along the heat transfer of thickness longitudinal, and ignores its lateral heat transfer, therefore
It can be reduced to one-dimensional unsteady heat conduction problem, Fig. 2 is the conduction model figure of non-corrosion area, constructs the model of non-corrosion area；
Heat Conduction Differential Equations:
Primary condition: t (x, 0)=t0 (4)
Boundary condition:
In formula, x is the value in thickness direction of metal component, and τ is heating time, and t (x, τ) is the temperature at τ moment at x
Degree, a2For the thermal diffusivity of non-corrosion layer, t0For environment temperature namely the initial temperature of metal component, h is the surface of metal component
Heat transfer coefficient, tfFor heating temperature, λ2For the metallic thermal conductivity of non-corrosion layer, δ is the thickness of metal component, and t (0, τ) is metal
The temperature at component surface τ moment, t (δ, τ) are the temperature at τ moment at metal component δ thickness；
This partial differential equation can be solved by the separation of variable or Green Function Method are as follows:
In formula, AkFor k-th of coefficient of Fourier expansion, βkFor k-th of characteristic value；
By characteristic equationSolve characteristic value βk, and 0 < β1<β2<β3<…<βk, according to initial
Condition t (x, 0)=t0, the coefficient A of Fourier expansion is acquired using Fourier expansion (Fourier series)k, because in solution of equation
Infinite series gradually decay, therefore it is approximate that first few items can be taken to make as one sees fit according to the needs of detection accuracy；
Due to thermal imaging system acquisition be metal component surface temperature information, i.e. t (0, τ) is known quantity, is denoted as Tb, use
Partial differential equation shown in formula (8) indicate the temperature T of non-corrosion areabAre as follows:
S42 Fig. 3 is the conduction model figure of corrosion area, the model for the corrosion area that building corrosion depth is Dep；
Heat Conduction Differential Equations:
Primary condition: ti(x, 0)=t0(i=1,2) (10)
Boundary condition:
(t1-t2)|X=Dep=0 (13)
In formula, when i=1, indicates corrosion layer, and when i=2 indicates non-corrosion layer, aiIndicate i-th layer of thermal diffusivity, λiIt indicates
I-th layer of metallic thermal conductivity, ti(x, τ) is the temperature at τ moment at i-th layer of x, ti(x, 0) is the initial temperature at i-th layer of x, t1
It (0, τ) is the temperature at corrosion layer surface τ moment, λ1For the metallic thermal conductivity of corrosion layer, λ2For the metallic thermal conductivity of non-corrosion layer,
t2(δ, τ) is the temperature at τ moment at metal component δ thickness, t1For the temperature of corrosion layer, t2For the temperature of non-corrosion layer；
It can Xie Chu this differential equation by the separation of variable of extension are as follows:
In formula, t1(x, τ) is the temperature at τ moment at corrosion layer x, t2(x, τ) is the temperature at τ moment at non-corrosion layer x, Bk
For k-th of coefficient of Fourier expansion, CkFor k-th of coefficient of Fourier expansion, γkFor k-th of characteristic value, μkFor k-th of spy
Value indicative；
Characteristic value γ is solved as the characteristic equation group as shown in formula (16)kAnd μk, and 0 < γ1<γ2<γ3<…<γk、0<
μ1<μ2<μ3<…<μk, wherein γkAnd μkIt is the function about corrosion depth Dep；
According to primary condition ti(x, 0)=t0(i=1,2) acquires each term system using Fourier expansion (Fourier series)
Number BkAnd Ck, because the infinite series in solution of equation are gradually decayed, can be taken as one sees fit according to the needs of detection accuracy former
Item is made approximate；
That thermal imaging system acquires is the temperature information of metal component surface, i.e. t1(0, τ) is known quantity, is denoted as T1, with above
The solution of partial differential equation can be by the temperature T of corrosion area1It indicates are as follows:
S43 formula (8) and formula (17) are the Implicitly functions about corrosion depth Dep, obtain the implicit of corrosion depth Dep
Function are as follows:
Corrosion depth Dep can be abbreviated as Dep=f3(ai,t0,tf,λi,τ,Tb,T1), it, will according to the condition of infrared detection
The temperature T of corrosion area1As input, corrosion depth Dep can be obtained；
As the temperature T of corrosion area1For each pixel temperature when, can get the corrosion depth of each pixel, work as corrosion
The temperature T in region1For corrosion area mean temperature when, can get corrosion area average corrosion depth, when corrosion area
Temperature T1For corrosion area maximum temperature when, can get corrosion area maximum corrosion depth.
The infrared image of metal component is obtained using metal component corrosion condition infrared detection system as shown in Figure 4, it should
System includes computer analytical equipment 1, infrared thermal imaging equipment 2 and blast heater 3, and wherein infrared thermal imaging equipment 2 passes through number
It is connect according to line with computer analytical equipment 1, and the camera lens of infrared thermal imaging equipment 2 is located at the front of detection coil, when work
Blast heater 3 carries out hot load to metal component 4, can change the thermal diffusivity and heat storage performance of metal due to corroding, rotten
The temperature for losing region can be higher than non-corrosion area, so that formation temperature is poor, by infrared thermal imaging equipment 2 to metal component 4
Surface temperature field carry out real-time infrared image acquisition, by collected infrared image delivery into computer analytical equipment 1.
In a preferred embodiment of the invention, infrared thermal imaging equipment 2 uses FLIR A320 model, metal component
For automobile B-column, infrared thermal imaging equipment 2 fixed first, and by the detection position of its alignment lens metal component 4, distance of camera lens
The metal component 4 about 0.5m adjusts focal length, sets initial temperature as room temperature, and is connected infrared thermal imaging equipment 2 by data line
It is connected to computer 1；
Heat is carried out to metal component 4 using hot air apparatus 3 and is loaded onto 50-100 DEG C so that metal component corrosion area with not
Corrosion area formation temperature is poor, carries out real-time infrared image using surface temperature field of the infrared thermal imaging equipment 2 to metal component
Acquisition, and information conveyance will be acquired to computer analysis platform；
Finally, using whether there is temperature in metal component corrosion condition detection method provided by the invention analysis infrared image
The area and color difference for spending abnormal region and temperature anomaly region, determine corroded area and corrosion depth with this.
As it will be easily appreciated by one skilled in the art that the foregoing is merely illustrative of the preferred embodiments of the present invention, not to
The limitation present invention, any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should all include
Within protection scope of the present invention.
Claims (7)
1. a kind of infrared detection method of metal component corrosion condition, which is characterized in that this method comprises the following steps:
S1 obtains the infrared image of metal component and carries out filtering and noise reduction processing, and then given threshold obtains the infrared image
Binary image；
S2 is according to the connectivity of pixel pixel adjacent thereto each in the binary image, indicia etched region and non-corrosion region
Domain, and draw the profile of the corrosion area；
The mask of S3 corrosion area in the binary image according to the contours extract of the corrosion area, using the mask in institute
State the temperature that the corrosion area is calculated in infrared image；
For S4 by the temperature input temp corrosion depth transformation model of the corrosion area, the corrosion for obtaining the metal component is deep
Degree.
2. the infrared detection method of metal component corrosion condition as described in claim 1, which is characterized in that in step sl,
Denoising is filtered using the method that edge retains filtering.
3. the infrared detection method of metal component corrosion condition as claimed in claim 1 or 2, which is characterized in that in step S1
In, the binary image of the infrared image is obtained using Otsu Binarization methods or maximum normalization temperature differential method.
4. the infrared detection method of metal component corrosion condition as claimed in any one of claims 1 to 3, which is characterized in that
In step S3, the temperature of the corrosion area include the temperature of each pixel in the corrosion area, the corrosion area it is flat
The maximum temperature of equal temperature or the corrosion area.
5. the infrared detection method of metal component corrosion condition as described in claim 1, which is characterized in that in step s 4,
The Implicitly function of corrosion depth in the temperature corrosion depth transformation model are as follows:
In formula, AkFor k-th of coefficient of Fourier expansion, βkFor k-th of characteristic value, BkFor k-th of coefficient of Fourier expansion,
γkIt is the function about corrosion depth for k-th of characteristic value, τ is heating time, a1For the thermal diffusivity of corrosion layer, a2For
The thermal diffusivity of non-corrosion layer, δ are the thickness of metal component, t0For the initial temperature of metal component, tfFor heating temperature, λ1For
The metallic thermal conductivity of corrosion layer, λ2For the metallic thermal conductivity of non-corrosion layer, h is the surface coefficient of heat transfer of metal component, TbIt is not rotten
Lose the temperature in region, T1For the temperature of corrosion area.
6. the infrared detection method of metal component corrosion condition as claimed in claim 5, which is characterized in that in step s 4,
The construction method of the temperature corrosion depth transformation model includes following sub-step:
S41 constructs the model of non-corrosion area, obtains the temperature T of non-corrosion areabAre as follows:
S42 constructs the model for the corrosion area that corrosion depth is Dep, obtains the temperature T of the corrosion area1Are as follows:
S43 obtains the Implicitly function of corrosion depth Dep according to formula (two) and formula (three) are as follows:
7. the infrared detection method of the metal component corrosion condition as described in claim 1, which is characterized in that in step S2
In, it further include the area that the corrosion area is calculated according to the profile of the corrosion area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910316762.5A CN110057745B (en) | 2019-04-19 | 2019-04-19 | Infrared detection method for corrosion condition of metal component |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910316762.5A CN110057745B (en) | 2019-04-19 | 2019-04-19 | Infrared detection method for corrosion condition of metal component |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110057745A true CN110057745A (en) | 2019-07-26 |
| CN110057745B CN110057745B (en) | 2020-07-10 |
Family
ID=67319713
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910316762.5A Active CN110057745B (en) | 2019-04-19 | 2019-04-19 | Infrared detection method for corrosion condition of metal component |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110057745B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112233109A (en) * | 2020-11-05 | 2021-01-15 | 北京理工大学 | Visible light interference resistant metal feeding visual sorting method |
| CN112251752A (en) * | 2020-12-23 | 2021-01-22 | 成都裕鸢航空零部件制造有限公司 | Method for removing broken tap or broken screw and filling device |
| CN117309668A (en) * | 2023-09-21 | 2023-12-29 | 东南大学 | Portable automatic detection equipment and detection method for steel wire corrosion |
| CN117309668B (en) * | 2023-09-21 | 2024-05-31 | 东南大学 | Portable automatic detection equipment and detection method for steel wire corrosion |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103111427A (en) * | 2013-01-10 | 2013-05-22 | 上海交通大学 | Fruit grader based on image processing |
| CN109448009A (en) * | 2018-11-21 | 2019-03-08 | 国网江苏省电力有限公司扬州供电分公司 | Infrared Image Processing Method and device for transmission line faultlocating |
-
2019
- 2019-04-19 CN CN201910316762.5A patent/CN110057745B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103111427A (en) * | 2013-01-10 | 2013-05-22 | 上海交通大学 | Fruit grader based on image processing |
| CN109448009A (en) * | 2018-11-21 | 2019-03-08 | 国网江苏省电力有限公司扬州供电分公司 | Infrared Image Processing Method and device for transmission line faultlocating |
Non-Patent Citations (2)
| Title |
|---|
| 王永茂 等: "缺陷大小和深度的红外检测", 《无损检测》 * |
| 胡林海: "基于红外热成像技术的金属材料缺陷定量评估研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112233109A (en) * | 2020-11-05 | 2021-01-15 | 北京理工大学 | Visible light interference resistant metal feeding visual sorting method |
| CN112233109B (en) * | 2020-11-05 | 2022-10-14 | 北京理工大学 | Visible light interference resistant metal feeding visual sorting method |
| CN112251752A (en) * | 2020-12-23 | 2021-01-22 | 成都裕鸢航空零部件制造有限公司 | Method for removing broken tap or broken screw and filling device |
| CN117309668A (en) * | 2023-09-21 | 2023-12-29 | 东南大学 | Portable automatic detection equipment and detection method for steel wire corrosion |
| CN117309668B (en) * | 2023-09-21 | 2024-05-31 | 东南大学 | Portable automatic detection equipment and detection method for steel wire corrosion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110057745B (en) | 2020-07-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108198181B (en) | Infrared thermal image processing method based on region segmentation and image fusion | |
| Yang et al. | Infrared thermal imaging-based crack detection using deep learning | |
| Jahanshahi et al. | A new methodology for non-contact accurate crack width measurement through photogrammetry for automated structural safety evaluation | |
| CN106950276B (en) | Pipeline defect depth inversion method based on convolutional neural network | |
| EP2350627B1 (en) | Method for detecting defect in material and system for the method | |
| Liu et al. | Window feature-based two-stage defect identification using magnetic flux leakage measurements | |
| CN112330538B (en) | Damage temperature reconstruction image splicing method based on feature point optimization extraction | |
| CN110057745A (en) | A kind of infrared detection method of metal component corrosion condition | |
| Jang et al. | Automated bridge crack evaluation through deep super resolution network-based hybrid image matching | |
| Mosdorf et al. | Detection of two-phase flow patterns using the recurrence network analysis of pressure drop fluctuations | |
| CN109724703A (en) | Temperature correction method under complex scene based on pattern-recognition | |
| Hu et al. | Rail surface spalling detection based on visual saliency | |
| Liu et al. | Detecting cracks in concrete structures with the baseline model of the visual characteristics of images | |
| Sreeshan et al. | Nondestructive inspection of aerospace composite laminate using thermal image processing | |
| CN110413942B (en) | Lane line equation screening method and screening module thereof | |
| Chen et al. | An intelligent vision recognition method based on deep learning for pointer meters | |
| Xie et al. | Automated leakage detection method of pipeline networks under complicated backgrounds by combining infrared thermography and Faster R-CNN technique | |
| Vorajee et al. | Analyzing capacity of a consumer-grade infrared camera in South Africa for cost-effective aerial inspection of building envelopes | |
| Guofeng et al. | Image segmentation of thermal waving inspection based on particle swarm optimization fuzzy clustering algorithm | |
| CN106706216A (en) | Non-contact detection method for leakage of gas with temperature higher than environment temperature | |
| CN110880170B (en) | Depth prediction method for composite material defects | |
| CN111445480B (en) | Image rotation angle and zoom coefficient measuring method based on novel template | |
| Kerscher et al. | Steel type determination by spark test image processing with machine learning | |
| CN109816651B (en) | Thermal image defect feature extraction method based on change rate and temperature difference | |
| Tröger et al. | Identification of the thermal conductivity tensor for transversely isotropic materials |
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 |