CN103909348B - A kind of ONLINE RECOGNITION incident laser departs from the method for state - Google Patents
A kind of ONLINE RECOGNITION incident laser departs from the method for state Download PDFInfo
- Publication number
- CN103909348B CN103909348B CN201410103456.0A CN201410103456A CN103909348B CN 103909348 B CN103909348 B CN 103909348B CN 201410103456 A CN201410103456 A CN 201410103456A CN 103909348 B CN103909348 B CN 103909348B
- Authority
- CN
- China
- Prior art keywords
- laser
- incident laser
- state
- departs
- frequency
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000003466 welding Methods 0.000 claims abstract description 36
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 claims abstract description 32
- 229910002092 carbon dioxide Inorganic materials 0.000 claims abstract description 16
- 239000001569 carbon dioxide Substances 0.000 claims abstract description 16
- 238000004458 analytical method Methods 0.000 claims abstract description 8
- 230000011218 segmentation Effects 0.000 claims description 8
- 238000013016 damping Methods 0.000 claims description 6
- 238000000513 principal component analysis Methods 0.000 claims description 6
- 230000005855 radiation Effects 0.000 claims description 4
- 230000003313 weakening effect Effects 0.000 claims description 4
- 230000010354 integration Effects 0.000 claims description 2
- 238000001228 spectrum Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000007789 gas Substances 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 2
- 229910052802 copper Inorganic materials 0.000 description 2
- 239000010949 copper Substances 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 229910001209 Low-carbon steel Inorganic materials 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 239000001307 helium Substances 0.000 description 1
- 229910052734 helium Inorganic materials 0.000 description 1
- SWQJXJOGLNCZEY-UHFFFAOYSA-N helium atom Chemical compound [He] SWQJXJOGLNCZEY-UHFFFAOYSA-N 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
- 238000005476 soldering Methods 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000005496 tempering Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K26/00—Working by laser beam, e.g. welding, cutting or boring
- B23K26/02—Positioning or observing the workpiece, e.g. with respect to the point of impact; Aligning, aiming or focusing the laser beam
- B23K26/04—Automatically aligning, aiming or focusing the laser beam, e.g. using the back-scattered light
- B23K26/044—Seam tracking
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K26/00—Working by laser beam, e.g. welding, cutting or boring
- B23K26/20—Bonding
- B23K26/21—Bonding by welding
- B23K26/24—Seam welding
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K2101/00—Articles made by soldering, welding or cutting
- B23K2101/18—Sheet panels
- B23K2101/185—Tailored blanks
Abstract
The invention discloses a kind of method that ONLINE RECOGNITION incident laser departs from state, weld for sandwich structure metallic plate carbon dioxide laser, in welding process, adopt high speed camera to take photic plasma cloud image, carry out the calculating of plasma cloud image features subsequently, and in setting-up time section the process statistics amount of computed image characteristic parameter, by principal component analytical method determination overall target, finally complete the judgement to incident laser position departure degree according to overall target.Method of the present invention can in sandwich structure metallic plate carbon dioxide laser weldering process accurately, the laser incoming position that forms a prompt judgement depart from state, device is simple and do not disturb laser beam welding, can be widely used in the carbon dioxide laser welding field of sandwich structure metallic plate.
Description
Technical field
The present invention relates to carbon dioxide laser welding technology field, be specifically related to a kind of in sandwich structure metallic plate carbon dioxide laser weldering process ONLINE RECOGNITION incident laser depart from the method for state.
Background technology
Sandwich steel plate, as light structures, has the advantages such as light specific gravity, good rigidly, strong shock resistance, increasingly extensive in the application in the fields such as boats and ships, bridge and building.Usually, panel and the central layer of sandwich structure are connected by the high power laser light weldering of T junction, and namely laser is radiated on panel, reaches central layer and cause the fusing of central layer by the keyhole on panel, the final welding formed between panel and central layer.This special welding manner requires that incident laser aims at central layer center line, but in actual production process, the factor such as rigging error, workpiece deformation can cause incident laser to depart from central layer.On the other hand, central layer by panel mask, cannot provide groove image in welding process, and this makes traditional welding seam tracking method cannot use in sandwich structure metallic plate Laser Welding.Retrieval finds, the achievement that this field is representative at present comprises:
1) patent " sandwich structure soldering point is simple and easy prepares platform and preparation method " (application number: 200710042738.4) described method is the positioner for the spot welding of small size sandwich structure, make the strict centering in copper rod termination by sleeve, and then in tempering furnace, complete the connection of two copper rods.This method does not have feasibility in the laser welding processes of sandwich structure metallic plate.
2) (application number: the welding seam tracking method 200910012657.9) completes based on the light line information of groove or joint can only be applicable to dock or the Laser Welding of lap joint patent " a kind of laser weld seam tracking device and control method thereof ".For the Laser Welding of sandwich structure, panel covers central layer completely, and in laser incidence, place does not exist any docking or lap joint affects light print image.
3) patent " active short wavelength laser weld keyhole monitoring and weld joint tracking integrating device " (application number: 201110382357.7) aperture of weld joint tracking and welding process is monitored be integrated in a set of imaging system, but with regard to weld joint tracking, remain the method based on joint image, which limits its application in sandwich structure.
4) patent " based on crater image visual sensing laser lap weldering between clearance detecting system and method " (application number: 201310413452.8) propose and detect the detection method in sandwich structure laser welding system gap based on crater image, the method judges the gap of T-shaped lap joint by the edge and area calculating crater image.On the one hand, in the information disclosed in it, do not relate to the departure degree whether this method can be used for judging incident laser; On the other hand, in carbon dioxide laser weldering process, the intense radiation of photo plasma can cause severe jamming to crater image, to the exposure intensity of secondary light source, and the synchronism of light source and camera is proposed very high requirement, therefore detection system is very complicated and expensive.
It can thus be appreciated that, at present also effective means is lacked to the ONLINE RECOGNITION that the incident laser of the high power laser light deep penetration welding of sandwich structure metallic plate departs from state, the acceptable splice between panel and central layer cannot be ensured, thus the final mechanical property weakening sandwich structure, even cause serious potential safety hazard.
Therefore, those skilled in the art be devoted to provide a kind of in sandwich structure metallic plate carbon dioxide laser weldering process ONLINE RECOGNITION incident laser depart from the method for state.
Summary of the invention
Because the above-mentioned defect of prior art, technical problem to be solved by this invention is to provide a kind of ONLINE RECOGNITION method incident laser being departed to central layer state in sandwich structure metallic plate carbon dioxide laser weldering process.
For achieving the above object, the present invention proposes a kind of method that ONLINE RECOGNITION incident laser departs from state, weld for sandwich structure metallic plate carbon dioxide laser, comprise the following steps: high speed camera is fixed on incident laser rear along welding direction, and in welding process, photic plasma cloud is taken continuously; Digital image processing techniques are adopted to complete the pretreatment of article on plasma cloud atlas picture; Extract the characteristic parameter of plasma cloud image, and specify the statistic calculating these image features in welding section; By principal component analysis technology determination principal component component and overall target, judge that the laser of corresponding welding process departs from state according to the result of calculation of welding process overall target.
Further, pretreatment comprises image enhaucament, binaryzation, Iamge Segmentation, edge extracting and image integration; Described Iamge Segmentation refers to and Iamge Segmentation is become background and target, and background B represents, target refers to plasma cloud, and target P represents.
Further, characteristic parameter comprises the height of plasma cloud, angle, accumulative gray scale and entropy;
Accumulative gray scale I
pcomputing formula be:
In above formula: g
i,jand k
i,jbe gray value and the weight of the pixel (i, j) in plasma cloud image respectively, i and j represents this pixel line number in the picture and columns; Z is constant coefficient, herein z=1000;
The computing formula of entropy is:
In above formula: x represents the tonal gradation of pixel; N represents the tonal gradation of image, for 8 gray level images, and n=255; T is the threshold value of Iamge Segmentation; The ratio of p (x) shared by tonal gradation x.
Further, process statistics amount comprises average, the coefficient of variation and frequency ratio;
The coefficient of variation refers to the ratio of data variance and average, for the decentralization of Description Image characteristic parameter in assignment procedure;
Frequency ratio is defined as: carry out Fast Fourier Transform (FFT) to the process feature parameter of fixed time section, obtain its frequency spectrum profile, add up the low frequency of setting and high frequency band signal amplitude respectively, high band adds up the ratio that amplitude and low-frequency range add up amplitude and is referred to as frequency ratio.In the present invention, section computing time of frequency ratio is 1 second, namely in welding process at interval of once calculating for 1 second; Low-frequency range is 100 ~ 200Hz, and high band is 300 ~ 400Hz.
Further, 4 characteristic parameters and 3 process statistics amounts combine, and can obtain 12 parameter values, i.e. the average x of height
1, coefficient of variation x
2x is compared with frequency
3, the average x of angle
4, coefficient of variation x
5x is compared with frequency
6, the average x of accumulative gray scale
7, coefficient of variation x
8x is compared with frequency
9, and the average x of entropy
10, coefficient of variation x
11x is compared with frequency
12.
Further, first principal component analysis is carried out for known sample, namely completes the carbon dioxide laser weldering that difference departs from state, calculates the parameter value that welding process is corresponding, by principal component analytical method, information merging is carried out to parameter value, determine the principal component component that at least can characterize 85% information content; And obtain final overall target according to the contribution degree of each principal component.
Further, the relative position of high speed camera and laser work head keeps constant in welding process, and is arranged in incident laser rear along welding direction, with the angle of incident laser axis 30 ~ 50 degree of scopes.
Further, the shooting speed of high speed camera when picture size is 150 pixel × 150 pixel is equal to or greater than 200 frames/second.
Further, high speed camera is furnished with light damping plate and UV sheet, and wherein light damping plate is for weakening the radiation light intensity of plasma cloud, and UV sheet is for the protection of camera lens.
Method of the present invention has following beneficial effect compared to existing technology: the present invention can depart from state for the incident laser of sandwich structure metallic plate laser beam welding and carry out ONLINE RECOGNITION, the method can when central layer be completely by panel mask, adopt the photic plasma cloud of high speed camera shooting welding process, overall target is extracted by Digital Image Processing and principal component analytical method, thus accurately, complete ONLINE RECOGNITION incident laser being departed to state rapidly, the method device is simple, and laser beam welding is not disturbed, the carbon dioxide laser welding field of sandwich structure metallic plate can be widely used in.
Be described further below with reference to the technique effect of accompanying drawing to design of the present invention, concrete structure and generation, to understand object of the present invention, characteristic sum effect fully.
Accompanying drawing explanation
Fig. 1 is the schematic diagram that in carbon dioxide laser weldering, incident laser departs from central layer;
Fig. 2 is the on-line monitoring recognition device structure chart of a preferred embodiment of the present invention;
Fig. 3 is the size characteristic parameter schematic diagram of photic plasma cloud image;
Fig. 4 calculates by rear 21 groups of data the overall target distribution map obtained in following embodiment.
Detailed description of the invention
Below embodiments of the invention are elaborated, the present embodiment premised on technical solution of the present invention under implement, give detailed embodiment and specific operation process, but protection scope of the present invention is not limited to following embodiment.
The invention discloses a kind of method that ONLINE RECOGNITION incident laser departs from state, weld for sandwich structure metallic plate carbon dioxide laser.As shown in Figure 1, X represents abscissa, and Y represents ordinate, goes out incident laser 31 project on panel 1 from laser work hair, and what is called departs from state and refers to distance δ between incident laser center line 30 and central layer center line 20.In high power carbon dioxide laser weldering process, if this bias exceedes certain limit, panel 1 can be affected with the bonding strength of central layer 2, thus finally causes the mechanical property of sandwich structure metallic plate significantly to decline.
High power laser light alleged by the present invention refers to that power is greater than the laser of 6kW, and the laser power in this example is 12kW, and laser spot diameter is 0.8mm.The material used is mild steel peculiar to vessel.The panel 1 of sandwich structure metallic plate sample is of a size of 200mm (length) × 200mm (wide) × 5mm (thick), and central layer 2 is of a size of 200mm (length) × 5mm (wide) × 50mm (height).Consider width and the laser spot diameter of central layer 2, after the bias of incident laser is more than 2.1mm, the stability of keyhole is affected, and panel 1 sharply declines with the connection width of central layer 2, therefore, in actual welding process, this situation should be identified and intervene.
As shown in Figure 2, the present embodiment on-line monitoring recognition device comprises: panel 1, central layer 2, laser work head 3, high speed camera 4, camera lens 5, side-blown gas nozzle 6.High speed camera 4 is furnished with light damping plate and UV sheet, and wherein light damping plate is for weakening the radiation light intensity of plasma cloud, and UV sheet is for the protection of camera lens 5.
Panel 1 and central layer 2 are also fixed by Fixture assembly, adopt laser spot welding to fix before weldering at sample two ends.In welding process, laser work head 3 and high speed camera 4 are fixed; High speed camera 4 is arranged in incident laser rear along welding direction, with the angle of incident laser axis 30 ~ 50 degree of scopes; Side-blown gas nozzle 6 is positioned at incident laser front, and side-blown gas nozzle 6 sprays helium.Sample is uniform motion under servomotor drags.
The picture size that high speed camera 3 takes photic plasma cloud is 150 pixel × 150 pixels, and shooting speed is equal to or greater than 200 frames/second.Fig. 3 is shown in image and the analysis of shooting, and the height of plasma cloud refers to the vertical range of plasma cloud top to root, uses h
prepresent; The angle of plasma cloud refers to the size of plasma cloud center with angle between the line at root center and horizontal line, uses α
prepresent.
In this example, according to the bias of incident laser and central layer center line 20, welding process is divided into 5 groups, as shown in table 1 below, adopt different identifiers to mark the weld seam that difference departs from state in table.
Table 1 sandwich structure Laser Welding grouping situation and technological parameter
In upper table, the incident laser bias of the 1st group and the 5th group all exceedes allowed band, and the bias of the 2nd, 3,4 group is then acceptable, and both of these case can identify by method proposed by the invention accurately and rapidly.
In this example, often group completes 4 weld seams, obtains 84 groups of data altogether.Front 63 groups of inputs as principal component analysis in these data, table 2 lists the coefficient correlation of this part data value; Rear 21 groups then according to the comprehensive evaluation index formula unfolding calculation that principal component analysis obtains.
The coefficient correlation of table 2 principal component analysis input data
Adopt the front 63 groups of data analysis in principal component analytical method his-and-hers watches 2, table 3 lists gained
The characteristic value of principal component component, contribution rate and contribution rate of accumulative total.
The characteristic value of table 3 principal component component, contribution rate and contribution rate of accumulative total
Be greater than 85% this principle according to contribution rate of accumulative total, determine that the number of final principal component component is 4, as follows:
z
1=0.436x
1+0.087x
2-0.107x
3-0.026x
4-0.027x
5-0.003x
6+0.172x
7-0.057x
8+0.095x
9+0.207x
10+0.622x
11-0.564x
12
z
2=-0.135x
1+0.429x
2-0.39x
3+0.285x
4-0.108x
5+0.326x
6-0.034x
7+0.044x
8+0.244x
9-0.608x
10+0.119x
11-0.039x
12
z
3=0.152x
1+0.455x
2+0.327x
3-0.056x
4-0.366x
5-0.136x
6-0.046x
7+0.133x
8-0.041x
9-0.041x
10-0.526x
11-0.455x
12
z
4=0.425x
1-0.047x
2-0.022x
3-0.011x
4-0.132x
5+0.075x
6+0.445x
7-0.548x
8+0.378x
9-0.035x
10-0.246x
11-0.302x
12
On the basis of these four principal component components, with the contribution rate of each component for weight, linear combination is carried out to these four principal component components, thus obtains overall target z, be shown below:
The parameter of rear 21 bond pads processes is substituted into the computing formula of principal component component, obtain z respectively
1, z
2, z
3and z
4again these four principal component components and contribution rate thereof are substituted into overall target computing formula, in the diagram, wherein abscissa is the bias of incident laser in the z value obtained display, ordinate is the result of calculation of overall target, each group mark of sample and consistent in table 1.
As can be seen from Figure 4, the depart from state of overall target z to incident laser has good separating capacity, and the laser that therefore the method may be used for sandwich structure metallic plate laser beam welding departs from state ONLINE RECOGNITION.
More than describe preferred embodiment of the present invention in detail.Should be appreciated that those of ordinary skill in the art just design according to the present invention can make many modifications and variations without the need to creative work.Therefore, all technical staff in the art, all should by the determined protection domain of claims under this invention's idea on the basis of existing technology by the available technical scheme of logical analysis, reasoning, or a limited experiment.
Claims (8)
1. an ONLINE RECOGNITION incident laser departs from the method for state, it is characterized in that, described method is used for the weldering of sandwich structure metallic plate carbon dioxide laser, comprise the following steps: adopt high speed camera to take the image of photic plasma cloud, after the pretreatment of image is completed, calculate the characteristic parameter of every piece image, and the process statistics amount at the appointed time completing described characteristic parameter in section is extracted, according to the formulae discovery comprehensive index value that principal component analytical method is determined; What judge incident laser with described comprehensive index value departs from state;
Described characteristic parameter comprises the height of plasma cloud image, angle, accumulative gray scale and entropy;
Described accumulative gray scale I
prepresent, computing formula is:
In above formula: g
i,jand k
i,jbe gray value and the weight of single pixel in plasma cloud image respectively, i and j represents described pixel line number in the picture and columns; Z is constant coefficient, herein z=1000;
Described entropy E
prepresent, computing formula is:
In above formula: x represents the tonal gradation of pixel; N represents the tonal gradation of image, for 8 gray level images, and n=255; T is the threshold value of Iamge Segmentation; The ratio of p (x) shared by tonal gradation x.
2. a kind of ONLINE RECOGNITION incident laser as claimed in claim 1 departs from the method for state, and it is characterized in that, described pretreatment comprises image enhaucament, binaryzation, Iamge Segmentation, edge extracting and image integration; Described Iamge Segmentation refers to and Iamge Segmentation is become background B and target P, and target P refers to plasma cloud image.
3. a kind of ONLINE RECOGNITION incident laser as claimed in claim 1 departs from the method for state, it is characterized in that, described process statistics amount comprises average, the coefficient of variation and frequency ratio;
The described coefficient of variation refers to the ratio of data variance and average, for the decentralization of Description Image characteristic parameter in assignment procedure;
Described frequency ratio is defined as: carry out Fast Fourier Transform (FFT) to the characteristic parameter of fixed time section, obtain its frequency spectrum profile, add up the low frequency of setting and high frequency band signal amplitude respectively, high band adds up the ratio that amplitude and low-frequency range add up amplitude and is referred to as frequency ratio.
4. a kind of ONLINE RECOGNITION incident laser as claimed in claim 1 departs from the method for state, it is characterized in that, described characteristic parameter comprises height, angle, accumulative gray scale, entropy, described process statistics amount comprises average, the coefficient of variation, frequency ratio, described characteristic parameter and described process statistics amount combine, 12 parameter values can be obtained, i.e. the average x of height
1, coefficient of variation x
2x is compared with frequency
3, the average x of angle
4, coefficient of variation x
5x is compared with frequency
6, the average x of accumulative gray scale
7, coefficient of variation x
8x is compared with frequency
9, and the average x of entropy
10, coefficient of variation x
11x is compared with frequency
12.
5. a kind of ONLINE RECOGNITION incident laser as claimed in claim 1 departs from the method for state, it is characterized in that, first described principal component analysis is carried out for known sample, namely the carbon dioxide laser weldering that difference departs from state is completed, calculate the parameter value that welding process is corresponding, by principal component analytical method, information merging is carried out to parameter value, determine the principal component component that at least can characterize 85% information content; And obtain final overall target according to the contribution degree of each principal component.
6. a kind of ONLINE RECOGNITION incident laser as claimed in claim 1 departs from the method for state, it is characterized in that, the relative position of described high speed camera and laser work head keeps constant in welding process, and be arranged in incident laser rear along welding direction, with the angle of incident laser axis 30 ~ 50 degree of scopes.
7. a kind of ONLINE RECOGNITION incident laser as claimed in claim 1 departs from the method for state, it is characterized in that, the shooting speed of described high speed camera when picture size is 150 pixel × 150 pixel is equal to or greater than 200 frames/second.
8. a kind of ONLINE RECOGNITION incident laser as claimed in claim 1 departs from the method for state, it is characterized in that, described high speed camera is furnished with light damping plate and UV sheet, and wherein light damping plate is for weakening the radiation light intensity of plasma cloud, and UV sheet is for the protection of camera lens.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410103456.0A CN103909348B (en) | 2014-03-19 | 2014-03-19 | A kind of ONLINE RECOGNITION incident laser departs from the method for state |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410103456.0A CN103909348B (en) | 2014-03-19 | 2014-03-19 | A kind of ONLINE RECOGNITION incident laser departs from the method for state |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103909348A CN103909348A (en) | 2014-07-09 |
| CN103909348B true CN103909348B (en) | 2015-11-25 |
Family
ID=51035515
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410103456.0A Expired - Fee Related CN103909348B (en) | 2014-03-19 | 2014-03-19 | A kind of ONLINE RECOGNITION incident laser departs from the method for state |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103909348B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109447394A (en) * | 2018-09-14 | 2019-03-08 | 中国科学院空间应用工程与技术中心 | A kind of earth observation satellite mission effectiveness assessment indicator system and analysis method |
| CN112903952B (en) * | 2021-01-21 | 2022-05-27 | 北京航空航天大学 | Metal plate structure damage evaluation system and method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101400474A (en) * | 2006-02-01 | 2009-04-01 | 蒂森克虏伯钢铁股份公司 | Laser beam welding head |
| US8412371B2 (en) * | 2005-09-30 | 2013-04-02 | Nissan Motor Co., Ltd. | Laser welding system, laser welding method, and emitting device |
| CN103506756A (en) * | 2013-09-11 | 2014-01-15 | 上海交通大学 | Laser lap welding gap detecting system and laser lap welding gap detecting method based on molten pool image visual sensing |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004216418A (en) * | 2003-01-14 | 2004-08-05 | Komatsu Ltd | Laser beam machine |
| JP5577927B2 (en) * | 2010-08-04 | 2014-08-27 | トヨタ車体株式会社 | Laser processing detection system |
-
2014
- 2014-03-19 CN CN201410103456.0A patent/CN103909348B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8412371B2 (en) * | 2005-09-30 | 2013-04-02 | Nissan Motor Co., Ltd. | Laser welding system, laser welding method, and emitting device |
| CN101400474A (en) * | 2006-02-01 | 2009-04-01 | 蒂森克虏伯钢铁股份公司 | Laser beam welding head |
| CN103506756A (en) * | 2013-09-11 | 2014-01-15 | 上海交通大学 | Laser lap welding gap detecting system and laser lap welding gap detecting method based on molten pool image visual sensing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103909348A (en) | 2014-07-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | Deep learning based online metallic surface defect detection method for wire and arc additive manufacturing | |
| CN104914111B (en) | A kind of steel strip surface defect online intelligent recognition detecting system and its detection method | |
| CN102159940B (en) | Method for detecting defect in material and system for same | |
| Luo et al. | Estimation of keyhole geometry and prediction of welding defects during laser welding based on a vision system and a radial basis function neural network | |
| CN106442543A (en) | Detection method for identifying surface quality of continuous laser seam of metal workpiece online | |
| Dong et al. | Robust circular marker localization under non-uniform illuminations based on homomorphic filtering | |
| Zhang et al. | Analysis of characteristics of molten pool using cast shadow during high-power disk laser welding | |
| Nilsen et al. | Vision and spectroscopic sensing for joint tracing in narrow gap laser butt welding | |
| Li et al. | Experimental study of FLD0 for aluminum alloy using digital image correlation with modified ISO method | |
| KR20160026400A (en) | Method for monitoring defect in polaroid films | |
| CN106441584A (en) | Converter roughing slag detection method based on infrared temperature measurement | |
| CN103464906A (en) | Online detection method for laser welding quality | |
| Zhao et al. | Additive seam tracking technology based on laser vision | |
| CN103909348B (en) | A kind of ONLINE RECOGNITION incident laser departs from the method for state | |
| CN109297976B (en) | Laser penetration welding defect detection platform and method based on laser welding energy distribution | |
| Gao et al. | Multi-sensor information fusion for monitoring disk laser welding | |
| Reisgen et al. | Machine vision system for online weld pool observation of gas metal arc welding processes | |
| CN105689859A (en) | Connecting method and device for various metals | |
| Medina et al. | Comparison of visual and hyperspectral monitoring of the melt pool during Laser Metal Deposition | |
| Chen et al. | Elucidation of high-power disk laser welding phenomena by simultaneously observing both top and bottom of weldment | |
| Sheng et al. | Online detection method of weld penetration based on molten pool morphology and metallic vapor radiation for fiber laser welding | |
| Murao et al. | Concrete crack detection using uav and deep learning | |
| KR102271251B1 (en) | Displacement Measurement System and Method of Contactless Structure in the Imaging Processing Unit | |
| Sikström et al. | Prediction of penetration in one-sided fillet welds by in-process joint gap monitoring—an experimental study | |
| Huang et al. | Impact of camera vibration frequencies on image noise for unmanned aerial system applications |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20151125 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |