CN120219491A - A visual positioning method for welding thermoplastic material and metal material - Google Patents
A visual positioning method for welding thermoplastic material and metal material Download PDFInfo
- Publication number
- CN120219491A CN120219491A CN202510287473.2A CN202510287473A CN120219491A CN 120219491 A CN120219491 A CN 120219491A CN 202510287473 A CN202510287473 A CN 202510287473A CN 120219491 A CN120219491 A CN 120219491A
- Authority
- CN
- China
- Prior art keywords
- positioning
- welding
- face
- area
- obtaining
- 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
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30152—Solder
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30241—Trajectory
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to a welding visual positioning method for a thermoplastic material and a metal material. According to the method, the moving track of the butt joint material in the butt joint process is monitored in real time and recorded, a moving track curve with obvious characteristics is finally formed, the positioning error of the butt joint material in the moving process can be effectively analyzed based on the moving track curve, the material accumulation condition of an end surface area is detected in the welding process of two materials, the positioning deformation in the welding process can be reflected through the material accumulation condition, and finally, a positioning adjustment function can be constructed through the end surface accumulation unevenness and the positioning error.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a welding visual positioning method for a thermoplastic material and a metal material.
Background
Thermoplastic composite materials are widely used in the aerospace field as a novel light material, and dissimilar material connection of metal and thermoplastic composite materials is receiving attention because the dissimilar material connection can fully exert the respective advantages of the two materials. Friction stir welding, which is a low heat input welding technique, has great application potential in the field of dissimilar welding of metal and thermoplastic composite materials, the process is to weld by taking the friction heat between the stirring head rotating at high speed and the workpiece as the heat input, and has the advantages of short process period, simple operation, no environmental pollution and the like. Because the thermoplastic material and the metal material have obvious differences in thermal expansion coefficient, thermal conductivity, melting point and the like, the problems of thermal stress, deformation and the like easily occur in the welding process, and therefore, the high-precision positioning technology is important for ensuring the accuracy of the welding position. The sub-millimeter positioning accuracy can be realized through a visual positioning system and an image processing algorithm. And errors in the welding process are compensated through real-time monitoring and feedback, so that the welding precision and consistency are improved.
In the actual positioning process, because the material is not in a straight shape, the material can be positioned to generate errors due to the shape problem in the butt joint friction process, and the positioning errors can generate the condition that friction is heated unevenly, so that welding defects are generated in the end face welding process.
Disclosure of Invention
In order to solve the technical problems that positioning errors in the butt joint process cannot be identified and friction deformation in the welding process causes poor welding effect in the prior art, the invention aims to provide a welding visual positioning method for thermoplastic materials and metal materials, and the adopted technical scheme is as follows:
The invention provides a welding visual positioning method of a thermoplastic material and a metal material, which comprises the following steps:
The method comprises the steps of taking any one material between a thermoplastic material and a metal material as a fixed material and the other material as a butt joint material, and obtaining a moving track curve of the butt joint material and a welding end surface image in the process of moving the butt joint material to the fixed material for welding;
Constructing a search window in an end surface area in the welding end surface image by taking the end surface area as a center, and obtaining end surface stacking unevenness according to pixel value changes among different preset areas in the search window;
and constructing a positioning adjustment function on the basis of a Gaussian function according to the end face stacking unevenness and the positioning error, and controlling the positioning of the two welding materials by using the positioning adjustment function.
Further, the method for acquiring the movement track curve comprises the following steps:
And acquiring a moving image of the butt joint material in the butt joint process according to a fixed camera arranged on the fixed material, wherein the moving image comprises an end face of the butt joint material, the center of mass point of the end face of the butt joint material is taken as a reference point, the transverse distance in each moving process of the reference point is taken as an abscissa, the longitudinal distance is taken as an ordinate, and the moving track curve is drawn.
Further, the method for acquiring the positioning error comprises the following steps:
Obtaining the positioning characteristics of the reference point in the moving image according to the coordinates of the reference point, and obtaining the variation fluctuation degree of the positioning characteristics in the moving process of the butt joint material;
decomposing the movement track curve to obtain a period, a trend term and a residual term of the movement track curve;
and obtaining the positioning error according to the fluctuation degree of the change and the fluctuation of the curve.
Further, the method for acquiring the variation fluctuation degree comprises the following steps:
Taking the product of the range and the variance of the positioning feature during the movement of the interfacing material as the degree of variation fluctuation.
Further, the method for acquiring the curve volatility comprises the following steps:
Multiplying the variance of the data in the residual term and the mean value in the trend term, and taking the ratio of the product to the period size as the curve volatility.
Further, the method for acquiring the end face stacking unevenness includes:
In the search window, sequentially constructing analysis areas with the end surface area as a center according to a preset step length, taking a normal material area as a comparison area, analyzing pixel value differences between the analysis areas of each scale and the comparison area to obtain end surface stacking degree, analyzing pixel value distribution stability in the analysis areas of each scale to obtain end surface stacking roughness, and obtaining the end surface stacking unevenness according to the end surface stacking degree and the end surface stacking roughness.
Further, the method for acquiring the end face stacking degree comprises the following steps:
Taking the difference value of the gray value mean value between each analysis area and the corresponding comparison area as the stacking display characteristic of each analysis area, and taking the accumulated value of all the analysis areas as the end face stacking degree.
Further, the method for acquiring the end face stacking roughness comprises the following steps:
Taking the difference between the gray value of each pixel point in the analysis area and the gray average value of the analysis area as the gray deviation of each gray value for each analysis area of each scale;
The average roughness of all analysis areas was taken as the end face stacking roughness.
Further, the expression of the positioning adjustment function is:
Wherein f represents a positioning adjustment function value, K represents the end face stacking unevenness, q represents a positioning error, X represents a positional deviation between a butt joint material at a current position and a butt joint material at a previous moment, e represents a natural constant, and X is a positive integer 1 when welding is not started.
Further, the method for acquiring the positioning feature comprises the following steps:
And obtaining coordinates of the reference point in the moving image, and taking Euclidean distance between the coordinates and the origin of the moving image as the positioning characteristic.
The invention has the following beneficial effects:
According to the invention, the moving track of the butt-joint material in the butt-joint process is monitored in real time and recorded, and finally, the moving track curve with obvious characteristics is formed, the positioning error of the butt-joint material in moving can be effectively analyzed based on the moving track curve, and further, the positioning control can be performed according to the positioning error. Further in the welding process of two materials, detect the material accumulation condition in terminal surface region, can reflect the location deformation in the welding process through the material accumulation condition, finally accessible terminal surface piles up unevenness and positioning error and builds location adjustment function promptly, can regulate and control the location defect that butt joint process and welding in-process produced with location adjustment function, and then improve welding quality.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a welding process for welding thermoplastic material and metal material according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for visually locating a weld between a thermoplastic material and a metallic material according to one embodiment of the present invention;
fig. 3 is a schematic diagram of a movement track according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following description refers to the specific implementation, structure, characteristics and effects of a welding visual positioning method for thermoplastic materials and metal materials according to the invention by combining the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
Referring to fig. 1, a welding schematic diagram of a welding process of a thermoplastic material and a metal material is shown, wherein one material is selected as a fixing material in the welding process, a welding material B is used as the fixing material, a camera is arranged above the fixing material, a welding material a is a butt joint material, two welding materials are fixed by a fixing clamp, the welding material a and the welding material B are controlled to butt joint, high-speed rotation is performed after butt joint is completed, and a large amount of heat is generated by rotation friction so that contact surfaces of the two materials are melted, and welding is further achieved.
The following specifically describes a specific scheme of a welding visual positioning method for thermoplastic materials and metal materials provided by the invention with reference to the accompanying drawings.
Referring to fig. 2, a flowchart of a method for visually positioning welding between a thermoplastic material and a metal material according to an embodiment of the present invention is shown, where the method includes:
Step S1, taking any one material between the thermoplastic material and the metal material as a fixed material and the other material as a butt joint material, and obtaining a moving track curve of the butt joint material and a welding end surface image in the process of moving the butt joint material to the fixed material for welding.
In the embodiment of the invention, a metal material is selected as a fixing material, and a thermoplastic material is selected as a butt joint material. In the process of butt joint of the butt joint materials, images of the butt joint materials can be acquired through a computer vision method, then a moving track curve of the butt joint materials is drawn, and information such as positioning errors in the moving process of the butt joint materials can be determined according to the moving track curve. Further, in the butt welding process, welding end face images of two material contact faces are acquired, and in the subsequent steps, positioning defects in the friction welding process can be further judged by determining material accumulation conditions of the welding end faces.
Preferably, in one embodiment of the present invention, the method for acquiring a movement track curve includes:
and acquiring a moving image of the butt joint material in the butt joint process according to a fixed camera arranged on the fixed material, wherein the moving image comprises the end face of the butt joint material. In the embodiment of the present invention, considering that the end face of the friction welding processed material has a specific shape, such as a circle, a rectangle, or the like, the edge detection can be performed on the moving image, and the end face area is obtained by recognizing the shape of the edge profile. It should be noted that, methods such as edge detection and contour recognition are all well known to those skilled in the art, and are not described herein.
And drawing a moving track curve by taking an end face centroid point of the butt joint material as a reference point, taking a transverse distance in each moving process of the reference point as an abscissa and a longitudinal distance as an ordinate. Referring to fig. 3, a schematic diagram of a movement track according to an embodiment of the invention is shown.
In the embodiment of the invention, the position data of the butt joint material is acquired every second, so that a movement track curve is constructed.
And S2, obtaining a positioning error according to the fluctuation of the moving track curve, constructing a search window in an end surface area in the welding end surface image by taking the end surface area as a center, and obtaining end surface accumulation unevenness according to the pixel value change between different preset areas in the search window.
In the process of butting the butting material and the fixed material, because of the problems of mechanical vibration and material shape, certain bending deformation exists in the butting process, so that positioning errors are generated, and the moving track curve can represent the position characteristics of the butting material in the moving process, so that the positioning errors in the butting process can be obtained according to the fluctuation of the moving track curve, namely, the larger the fluctuation is, the more the positioning errors are generated.
Preferably, in an embodiment of the present invention, a method for acquiring a positioning error includes:
And obtaining the positioning characteristic of the reference point in the moving image according to the coordinates of the reference point. The positioning feature is used for converting two-dimensional coordinate information into one-dimensional numerical feature data, so that the position of the reference point can be conveniently quantized. And further, the variation fluctuation degree of the positioning features in the moving process of the butt joint material can be obtained, namely, the variation fluctuation degree can be obtained by counting the variation of the positioning features in the whole butt joint process.
In order to analyze the volatility of the movement track curve, the movement track curve is decomposed, and the period, the trend term and the residual term of the movement track curve are obtained. And obtaining the curve fluctuation of the movement track curve according to the period, the trend term and the residual term. The method is characterized in that the smaller the period is, the larger the fluctuation of the number of changes on the curve is, the larger the trend term is, the more complex the trend change is, the larger the curve fluctuation is, the larger the residual term is, the curve has obvious fluctuation, and the larger the fluctuation is when certain deviation exists between data.
And obtaining the positioning error according to the fluctuation degree of the change and the fluctuation of the curve. In the embodiment of the invention, after the fluctuation degree of the change and the fluctuation of the curve are quantized, the product of the fluctuation degree of the change and the fluctuation of the curve is used as a positioning error.
In the embodiment of the invention, the method for acquiring the positioning characteristics comprises the following steps:
and obtaining coordinates of the reference point in the moving image, and taking Euclidean distance between the coordinates and the origin of the moving image as a positioning feature. Namely, the positioning characteristics of the reference points are effectively quantified through Euclidean distance.
Further, the method for acquiring the fluctuation degree comprises the following steps:
because the position data of the butt joint material is obtained according to a certain sampling frequency, the positioning feature is equivalent to having a certain sampling frequency, and a positioning feature set is obtained in the butt joint process. The product of the range and the variance of the positioning feature during movement of the interfacing material is taken as the varying degree of fluctuation. The larger the range of the variation of the positioning feature is larger, the larger the variance is, the larger the variation degree of the positioning feature is, and therefore the product of the two can effectively represent the variation fluctuation.
Further, the method for acquiring the curve volatility comprises the following steps:
multiplying the variance of the data in the residual term and the mean value in the trend term, and taking the ratio of the product to the period size as curve volatility. In the embodiment of the present invention, the STL decomposition algorithm is used to decompose the movement track curve, and the specific method is a technical means well known to those skilled in the art, which is not described herein. The embodiment of the invention constructs the positive correlation and the negative correlation by a product and ratio method, and realizes the effective quantification of curve volatility.
In the friction welding process, the two materials are subjected to high-speed rotational friction, and heat is generated to melt-weld the end surfaces of the two materials. Under the process, the thermoplastic material can generate larger deformation relative to the metal material due to the softer property, and the deformation can lead to uneven stress of the material in the friction welding process and further lead to new positioning errors, and welding defects appear. In the friction welding process, in order to be able to weld the welding port firmly, a certain horizontal pressure can be applied to the welding material, so that the welding material is deformed to a certain extent, namely, the situation that the friction port is piled up, and the welding material slowly moves towards the welding port. Therefore, the welding quality can be determined by monitoring the accumulation condition of the excess materials in the end surface area in the friction welding process, and whether an error occurs or not can be judged. That is, the larger the accumulation degree of the residual materials is, the more the residual materials are increased due to the positioning offset generated in the welding process. Therefore, the embodiment of the invention utilizes an image processing technology to determine the end surface area in the welding end surface image, further constructs a search window by taking the end surface area as the center, and can obtain end surface accumulation unevenness by analyzing the pixel value changes among different preset areas in the search window. That is, the accumulation of the residual material occurs in the search window, and the pixel value of the accumulation area and the non-accumulation area inevitably generate obvious pixel value change, so that the end surface accumulation unevenness of the residual material on the end surface can be effectively obtained by analyzing different areas in the search window.
In the embodiment of the invention, because the welding end face image is an image of the welding process started, the end faces of two materials are contacted, so that an end face area forms a line segment on the image, and the line segment formed by the end face area can be directly obtained through edge detection.
Preferably, in one embodiment of the present invention, the method for acquiring end face pile-up unevenness includes:
In the search window, the analysis areas are sequentially constructed by taking the end surface area as the center according to a preset step length. In the embodiment of the invention, the search window is set to be an area which is expanded twenty times to two sides by taking the end surface area as the center, and the step length of each expansion is one pixel point, namely the final search window is a rectangular area with the length of 41 and the width of the length of a line segment formed by the end surface area. Setting the construction compensation of the analysis area as 2, namely expanding 2 pixel unit formation areas outwards each time, taking the analysis area constructed for the first time as an example, wherein the analysis area is a rectangular area with the length of 5 and the width of a line segment formed by the end surface area, and the analysis area constructed for the second time is a rectangular area with the length of 9 and the width of the line segment formed by the end surface area. And continuously expanding until the analysis area coincides with the search window, and ending the analysis.
Because the analysis area is obtained by expanding the end surface area as the center, the accumulation of the residual materials can be preferentially represented in the analysis area, the comparison area is a normal material area which is an area without residual material accumulation, the residual material accumulation area can show bright characteristics due to the influence of high temperature, and the normal material area is relatively dark. And therefore, the pixel value difference between the analysis area of each scale and other areas in the search window is analyzed, and the end face stacking degree is obtained. That is, the larger the difference in pixel value between the two regions, the more likely the analysis region is to be a residue accumulation region, and the greater the end face accumulation degree.
The accumulation of the residual materials in the image not only shows bright characteristics, but also shows the texture characteristics of the surface of the residual materials. And further analyzing the distribution stability of the pixel values in the analysis area of each scale to obtain the end face stacking roughness. That is, the worse the distribution stability of the pixel values in the analysis area, the more abundant the texture features, which means that the analysis area is more likely to be a residue accumulation area.
The end face stacking unevenness is obtained from the end face stacking degree and the end face stacking roughness. In the embodiment of the present invention, the end face accumulation degree and the end face roughness are quantized and then multiplied, and the product is used as the end face accumulation unevenness.
Further, in the embodiment of the present invention, the method for acquiring the stacking degree of the end surfaces includes:
And taking the difference value of the gray value mean value between each analysis area and the corresponding comparison area as the stacking display characteristic of each analysis area. That is, the larger the difference in the gray value means, the brighter the analysis area, the more likely the analysis area is that all of the rest is formed by accumulation. The accumulated value of all analysis areas was taken as the end face accumulation degree.
Further, in the embodiment of the present invention, the method for obtaining the stacking roughness of the end surface includes:
for each scale of analysis area, the difference between the gray value of each pixel point in the analysis area and the gray average value of the analysis area is used as the gray deviation of each gray value, and the average gray deviation of all the pixel points in the analysis area is used as the roughness of the analysis area. The larger the average gray scale deviation, the more uneven the pixel value distribution in the analysis area, the stronger the texture features and the larger the roughness in the area.
Since there are a plurality of scale analysis regions in the search window, the average roughness of all the analysis regions is taken as the end face stacking roughness.
And S3, constructing a positioning adjustment function on the basis of a Gaussian function according to the end face stacking unevenness and positioning errors, and controlling the positioning of the two welding materials by using the positioning adjustment function.
Based on the steps, analysis results of visual monitoring based on image information in real time in a butt joint process and a welding process can be obtained, and a positioning adjustment function in a positioning process can be constructed based on end face accumulation unevenness and positioning errors.
Preferably, in the embodiment of the present invention, the expression of the positioning adjustment function is:
Wherein f represents a positioning adjustment function value, K represents the end face stacking unevenness, q represents a positioning error, X represents a positional deviation between a butt joint material at a current position and a butt joint material at a previous moment, e represents a natural constant, and X is a positive integer 1 when welding is not started. When welding is not started, the butt joint process is described, and there is no welding process or analysis of end face accumulation unevenness, so that X can be set to 1 directly, and only positioning error information is retained.
It should be noted that, because X represents the position deviation of the butt-jointed material at adjacent moments, the position of the butt-jointed material determined in the butt-jointed process in the embodiment of the present invention is obtained by the end surfaces of the butt-jointed material, so that X may be set as the difference of the positioning features between the two moments, while the welding process has no complete end surface of the material, and only includes the line segment formed by the contact surface between the two materials, so that the difference of the positioning features of the positioning points may be obtained by taking the midpoint of the line segment as the positioning point.
The control module of the welding device can adaptively control the adjustment amount and perform positioning adjustment by referring to the output result of the positioning adjustment function, and a specific adjustment feedback method is a technical means well known to those skilled in the art, and will not be described herein.
In summary, the embodiment of the invention monitors and records the movement track of the butt joint material in real time in the butt joint process, finally forms a movement track curve with obvious characteristics, can effectively analyze the positioning error of the butt joint material in the movement process based on the movement track curve, detects the material accumulation condition of the end surface area in the welding process of two materials, can reflect the positioning deformation in the welding process through the material accumulation condition, and can finally construct a positioning adjustment function through the end surface accumulation unevenness and the positioning error.
It should be noted that the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510287473.2A CN120219491B (en) | 2025-03-11 | 2025-03-11 | Welding visual positioning method for thermoplastic material and metal material |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510287473.2A CN120219491B (en) | 2025-03-11 | 2025-03-11 | Welding visual positioning method for thermoplastic material and metal material |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN120219491A true CN120219491A (en) | 2025-06-27 |
| CN120219491B CN120219491B (en) | 2025-10-17 |
Family
ID=96107218
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510287473.2A Active CN120219491B (en) | 2025-03-11 | 2025-03-11 | Welding visual positioning method for thermoplastic material and metal material |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120219491B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR960037193A (en) * | 1995-04-27 | 1996-11-19 | 이종수 | Seam tracking method using vision system |
| JPH0999368A (en) * | 1995-10-05 | 1997-04-15 | Hitachi Ltd | Automatic welding equipment |
| US6581819B1 (en) * | 1996-03-19 | 2003-06-24 | Hitachi, Ltd. | Panel structure, a friction stir welding method, and a panel |
| KR20120014850A (en) * | 2010-08-10 | 2012-02-20 | 주식회사 성우하이텍 | Welding position inspection method |
-
2025
- 2025-03-11 CN CN202510287473.2A patent/CN120219491B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR960037193A (en) * | 1995-04-27 | 1996-11-19 | 이종수 | Seam tracking method using vision system |
| JPH0999368A (en) * | 1995-10-05 | 1997-04-15 | Hitachi Ltd | Automatic welding equipment |
| US6581819B1 (en) * | 1996-03-19 | 2003-06-24 | Hitachi, Ltd. | Panel structure, a friction stir welding method, and a panel |
| KR20120014850A (en) * | 2010-08-10 | 2012-02-20 | 주식회사 성우하이텍 | Welding position inspection method |
Non-Patent Citations (1)
| Title |
|---|
| 王力;王胜华;都东;: "机器人焊接轨迹自动跟踪视觉技术研究", 电焊机, no. 04, 20 April 2009 (2009-04-20) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN120219491B (en) | 2025-10-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | A robust weld seam recognition method under heavy noise based on structured-light vision | |
| Li et al. | Deep learning based online metallic surface defect detection method for wire and arc additive manufacturing | |
| Zong et al. | An intelligent and automated 3D surface defect detection system for quantitative 3D estimation and feature classification of material surface defects | |
| CN118602979B (en) | Weld joint morphology and surface defect online detection and evaluation method and system | |
| CN101559512B (en) | Welding track detection and control method of plate butt weld based on laser ranging | |
| CN115096206B (en) | A high-precision measurement method for part dimensions based on machine vision | |
| CN101387493B (en) | Non-contact photoelectric detection method for shape, position and size of iron tower component holes | |
| CN110064819A (en) | The extraction of cylinder longitudinal seam characteristic area, welding seam tracking method and system based on structure light | |
| CN117392134B (en) | On-line visual detection system for high-speed dispensing | |
| Zhou et al. | Autonomous nondestructive evaluation of resistance spot welded joints | |
| Tian et al. | Robust identification of weld seam based on region of interest operation | |
| Liu et al. | Detection and quantitative evaluation of surface defects in wire and arc additive manufacturing based on 3D point cloud | |
| CN120219491B (en) | Welding visual positioning method for thermoplastic material and metal material | |
| US20250259290A1 (en) | Systems and methods for post-repair inspection of a worksurface | |
| CN116912165A (en) | A method for detecting welding defects of aluminum alloy sheets based on improved YOLOv5 | |
| CN108389204B (en) | Degraded image fuzzy kernel double-parameter direct estimation method for high-speed online detection | |
| Wang et al. | Automatic identification, classification, localization and quantitative evaluation of surface defects for wire-arc directed energy deposition using deep learning and 3D point cloud processing | |
| CN119067976B (en) | A 3D printing anomaly detection and early warning method based on machine vision | |
| CN119927930A (en) | A method, system and medium for intelligent control of a robotic arm based on machine vision | |
| Zou et al. | Laser-based precise measurement of tailor welded blanks: a case study | |
| Lyu et al. | MScan: An Automated In-Situ Fault Detection System for Desktop Fused Filament Fabrication 3D Printers Utilizing a Non-Contact Sensor | |
| Sun et al. | Precision work-piece detection and measurement combining top-down and bottom-up saliency | |
| Mok et al. | Measurement of bending deformation of sheet metal using machine vision | |
| Cai et al. | A structured light-based visual sensing system for detecting multi-layer and multi-track welding | |
| Duan et al. | Research Review of Dispensing Based on Machine Vision |
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 |