Automatic on-line detection of welding deviation based on machine vision is one of the key technologies of arc welding robot tracking welding,in which obtaining high quality weld pool image and accurate welding deviat...Automatic on-line detection of welding deviation based on machine vision is one of the key technologies of arc welding robot tracking welding,in which obtaining high quality weld pool image and accurate welding deviation detection algorithm are two important steps of tracking welding.Through the research and analysis of the weld pool image of gas metal arc welding(GMAW),it was found that the weld pool contains abundant welding information.First,the average gray value of the weld pool image can reflect the interference degree of arc to weld pool image and the heat input of welding process.Secondly,the tip of the weld pool image contour can reflect the center of the groove gap.Finally,the horizontal distance between the center coordinate of the wire contour and the tip coordinate of the weld pool image contour can reflect the welding deviation.On the basis of analyzing the characteristics of weld pool image,this paper proposes a new method of weld seam deviation detection,which includes the collection of weld pool image,image preprocessing,contour extraction and deviation calculation.The results of the tests and analyses showed that the maximum error of the on-line welding deviation obtained was about 2 pixels(0.17 mm)when the welding speed was≤60 cm/min,and the algorithm was stable enough to meet the requirements of real-time deviation detection for I-groove butt welding.The method can be applied to the on-line automatic welding deviation detection of arc welding robot.展开更多
Visual image sensor is developed to detect the weld pool images in pulsed MIG welding. An exposure controller, which is composed of the modules of the voltage transforming, the exposure parameters presetting, the comp...Visual image sensor is developed to detect the weld pool images in pulsed MIG welding. An exposure controller, which is composed of the modules of the voltage transforming, the exposure parameters presetting, the complex programmable logic device （CPLD） based logic controlling, exposure signal processing, the arc state detecting, the mechanical iris driving and so on, is designed at first. Then, a visual image sensor consists of an ordinary CCD camera, optical system and exposure controller is established. The exposure synchronic control logic is described with very-high-speed integrated circuit hardware description language （VHDL） and programmed with CPLD , to detect weld pool images at the stage of base current in pulsed MIG welding. Finally, both bead on plate welding and V groove filled welding are carried out, clear and consistent weld pool images are acquired.展开更多
In order to discover characteristics of various kinds of weld pool image and identify a single image, seven image features are extracted to describe the corresponding surface formation quality by the moment iavariants...In order to discover characteristics of various kinds of weld pool image and identify a single image, seven image features are extracted to describe the corresponding surface formation quality by the moment iavariants method. An image feature matrix is composed by the seven characteristics. Then the matrix is projected on a line through the Fisher criterion in order to entirely distinguish various kinds of image features. And finally, transforming a seven-dimensional problem into a one-dimensional problem has been done. Compared with the three kinds of samples included in the arc welding process and quality weld pool visual image database, the images are classified into the three kinds such as superior weld formation in the condition of optimal gas flow, poor weld formation image in the condition of insuffwient gas flow, inferior weld formation in the condition of too low gas flow. Experiments show that the Fisher classification method based on moment invariants can recognize various weld pool images effectively, and it achieves a correct recognizable rate of 100%.展开更多
针对熔化极气体保护电弧(gas metal arc,GMA)增材制造(additive manufacturing,AM)图像感知,提出一种透红外熔池视觉传感方法.为客观评价熔池图像质量,综合图像灰度、纹理、形状和频谱等四类特征定义了熔池图像质量评价参数φ.结果表明...针对熔化极气体保护电弧(gas metal arc,GMA)增材制造(additive manufacturing,AM)图像感知,提出一种透红外熔池视觉传感方法.为客观评价熔池图像质量,综合图像灰度、纹理、形状和频谱等四类特征定义了熔池图像质量评价参数φ.结果表明,φ值越大,图像质量越好.透红外熔池图像质量评价参数φ远大于近红外窄带熔池图像,熔池更清晰,对比度更高.相比800,850和930 nm等透红外滤光片,990 nm透红外滤光片能过滤大部分电弧连续谱和特征谱,获得的熔池信息量最大,对比度更明显,边缘更清晰,细节信息更丰富,熔池图像质量最佳,是最佳取像窗口.展开更多
Abstract Image sensor has been one of the key technologies in intellectualized robotics welding. Edge detection plays an important role when the vision technology is applied in intellectualized welding robotics techno...Abstract Image sensor has been one of the key technologies in intellectualized robotics welding. Edge detection plays an important role when the vision technology is applied in intellectualized welding robotics technologies. There are all kinds of noises in welding environment. The algorithms in common use cannot be applied to the recognition of welding environment directly. The edge of images can be fell into four types. The weld images are classified by the characteristic of welding environment in this paper. This paper analyzes some algorithms of edge detection according to the character of welding image, some relative advantages and disadvantages are pointed out when these algorithms are used in this field, and some suggestions are given. The feature extraction of weld seam and weld pool are two typical problems in the realization of intellectualized welding. Their edge features are extracted and the results show the applicability of different edge detectors. The trndeoff between precision and calculated time is also considered for different application.展开更多
In order to obtain good welding quality, it is necessary to apply quality control because there are many influencing factors in laser welding process. The key to realize welding quality control is to obtain the qualit...In order to obtain good welding quality, it is necessary to apply quality control because there are many influencing factors in laser welding process. The key to realize welding quality control is to obtain the quality information. Abundant weld quality information is contained in weld pool and keyhole. Aiming at Nd：YAG laser welding of stainless steel, a coaxial visual sensing system was constructed. The images of weld pool and keyhole were obtained. Based on the gray character of weld pool and keyhole in images, an image processing algorithm was designed. The search start point and search criteria of weld pool and keyhole edge were determined respectively.展开更多
A passive visual sensing system is established in this research, and clear weld pool images in pulsed gas metal arc welding （ P-GMA W） can be captured with this system. The three-dimensional weld pool geometry, espe...A passive visual sensing system is established in this research, and clear weld pool images in pulsed gas metal arc welding （ P-GMA W） can be captured with this system. The three-dimensional weld pool geometry, especially the weld height, is not only a crucial factor in determining workpiece mechanical properties, but also an important parameter for reflecting the penetration. A new three-dimensional （3D） model is established to describe the weld pool geometry in P-GMAW. Then, a series of algorithms are developed to extract the model geometrical parameters from the weld pool images. Furthermore, the method to reconstruct the 3 D shape of weld pool boundary and weld bead from the two-dimensional images is investigated.展开更多
In manual welding process, skilled welders can adjust the welding parameters to ensure the weld quality through their observation of the weld pool surface. In order to acquire useful information of the weld pool for c...In manual welding process, skilled welders can adjust the welding parameters to ensure the weld quality through their observation of the weld pool surface. In order to acquire useful information of the weld pool for control of the welding process and realizing the automatic welding, the measurement system of DB-GMA W process was established and the weld pool image was obtained by passive vision. Then, three image processing algorithms, Sobel, Canny, and pulse coupled neural network （PCNN） were detailed and applied to extracting the edge of the DB-GMA weld pool. In addition, a scheme was proposed for calculating the length, maximum width and superficial area of the weld pool under different welding conditions. The compared results show that the PCNN algorithm can be used for extracting the edge of the weld pool and the obtained information is more useful and accurate. The calculated results coincide with the actual measurement well, which demonstrates that the proposed algorithm is effective, its imaging processing time is required only 20 ms, which can completely meet the requirement of real-time control.展开更多
基金supported by the National Natural Foundation of China(Grant No.51875384)the Natural Science Foundation of Shanxi Province(Grant No.201601D011036)the Natural Science Foundation of Shanxi Province(Grant No.201801D121082)
文摘Automatic on-line detection of welding deviation based on machine vision is one of the key technologies of arc welding robot tracking welding,in which obtaining high quality weld pool image and accurate welding deviation detection algorithm are two important steps of tracking welding.Through the research and analysis of the weld pool image of gas metal arc welding(GMAW),it was found that the weld pool contains abundant welding information.First,the average gray value of the weld pool image can reflect the interference degree of arc to weld pool image and the heat input of welding process.Secondly,the tip of the weld pool image contour can reflect the center of the groove gap.Finally,the horizontal distance between the center coordinate of the wire contour and the tip coordinate of the weld pool image contour can reflect the welding deviation.On the basis of analyzing the characteristics of weld pool image,this paper proposes a new method of weld seam deviation detection,which includes the collection of weld pool image,image preprocessing,contour extraction and deviation calculation.The results of the tests and analyses showed that the maximum error of the on-line welding deviation obtained was about 2 pixels(0.17 mm)when the welding speed was≤60 cm/min,and the algorithm was stable enough to meet the requirements of real-time deviation detection for I-groove butt welding.The method can be applied to the on-line automatic welding deviation detection of arc welding robot.
基金This work was supported by the National High Technology Research and Development Program("863"Program) of China ( ContractNo 2007AA04Z258)
文摘Visual image sensor is developed to detect the weld pool images in pulsed MIG welding. An exposure controller, which is composed of the modules of the voltage transforming, the exposure parameters presetting, the complex programmable logic device （CPLD） based logic controlling, exposure signal processing, the arc state detecting, the mechanical iris driving and so on, is designed at first. Then, a visual image sensor consists of an ordinary CCD camera, optical system and exposure controller is established. The exposure synchronic control logic is described with very-high-speed integrated circuit hardware description language （VHDL） and programmed with CPLD , to detect weld pool images at the stage of base current in pulsed MIG welding. Finally, both bead on plate welding and V groove filled welding are carried out, clear and consistent weld pool images are acquired.
基金Fund projects： National Natural Science Foundation of China（ No 51075214）funding.
文摘In order to discover characteristics of various kinds of weld pool image and identify a single image, seven image features are extracted to describe the corresponding surface formation quality by the moment iavariants method. An image feature matrix is composed by the seven characteristics. Then the matrix is projected on a line through the Fisher criterion in order to entirely distinguish various kinds of image features. And finally, transforming a seven-dimensional problem into a one-dimensional problem has been done. Compared with the three kinds of samples included in the arc welding process and quality weld pool visual image database, the images are classified into the three kinds such as superior weld formation in the condition of optimal gas flow, poor weld formation image in the condition of insuffwient gas flow, inferior weld formation in the condition of too low gas flow. Experiments show that the Fisher classification method based on moment invariants can recognize various weld pool images effectively, and it achieves a correct recognizable rate of 100%.
基金This research was supported by Research Foundation for Talented Scholars,Jiangsu University (07JDG085)Shanghai Science and Technology Committee (No021111116)
文摘Abstract Image sensor has been one of the key technologies in intellectualized robotics welding. Edge detection plays an important role when the vision technology is applied in intellectualized welding robotics technologies. There are all kinds of noises in welding environment. The algorithms in common use cannot be applied to the recognition of welding environment directly. The edge of images can be fell into four types. The weld images are classified by the characteristic of welding environment in this paper. This paper analyzes some algorithms of edge detection according to the character of welding image, some relative advantages and disadvantages are pointed out when these algorithms are used in this field, and some suggestions are given. The feature extraction of weld seam and weld pool are two typical problems in the realization of intellectualized welding. Their edge features are extracted and the results show the applicability of different edge detectors. The trndeoff between precision and calculated time is also considered for different application.
基金Project (10776020) supported by the Joint Foundation of the National Natural Science Foundation of China and China Academy of Engineering Physics
文摘In order to obtain good welding quality, it is necessary to apply quality control because there are many influencing factors in laser welding process. The key to realize welding quality control is to obtain the quality information. Abundant weld quality information is contained in weld pool and keyhole. Aiming at Nd：YAG laser welding of stainless steel, a coaxial visual sensing system was constructed. The images of weld pool and keyhole were obtained. Based on the gray character of weld pool and keyhole in images, an image processing algorithm was designed. The search start point and search criteria of weld pool and keyhole edge were determined respectively.
文摘A passive visual sensing system is established in this research, and clear weld pool images in pulsed gas metal arc welding （ P-GMA W） can be captured with this system. The three-dimensional weld pool geometry, especially the weld height, is not only a crucial factor in determining workpiece mechanical properties, but also an important parameter for reflecting the penetration. A new three-dimensional （3D） model is established to describe the weld pool geometry in P-GMAW. Then, a series of algorithms are developed to extract the model geometrical parameters from the weld pool images. Furthermore, the method to reconstruct the 3 D shape of weld pool boundary and weld bead from the two-dimensional images is investigated.
基金This work is supported by the National Natural Science Foundation of China under Grant No. 61365011.
文摘In manual welding process, skilled welders can adjust the welding parameters to ensure the weld quality through their observation of the weld pool surface. In order to acquire useful information of the weld pool for control of the welding process and realizing the automatic welding, the measurement system of DB-GMA W process was established and the weld pool image was obtained by passive vision. Then, three image processing algorithms, Sobel, Canny, and pulse coupled neural network （PCNN） were detailed and applied to extracting the edge of the DB-GMA weld pool. In addition, a scheme was proposed for calculating the length, maximum width and superficial area of the weld pool under different welding conditions. The compared results show that the PCNN algorithm can be used for extracting the edge of the weld pool and the obtained information is more useful and accurate. The calculated results coincide with the actual measurement well, which demonstrates that the proposed algorithm is effective, its imaging processing time is required only 20 ms, which can completely meet the requirement of real-time control.
