Edge detection and its application to recognition of arc weld image

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.

DGConv: A Novel Convolutional Neural Network Approach for Weld Seam Depth Image Detection

We propose a novel image segmentation algorithm to tackle the challenge of limited recognition and segmentation performance in identifying welding seam images during robotic intelligent operations.Initially,to enhance the capability of deep neural networks in extracting geometric attributes from depth images,we developed a novel deep geometric convolution operator(DGConv).DGConv is utilized to construct a deep local geometric feature extraction module,facilitating a more comprehensive exploration of the intrinsic geometric information within depth images.Secondly,we integrate the newly proposed deep geometric feature module with the Fully Convolutional Network(FCN8)to establish a high-performance deep neural network algorithm tailored for depth image segmentation.Concurrently,we enhance the FCN8 detection head by separating the segmentation and classification processes.This enhancement significantly boosts the network’s overall detection capability.Thirdly,for a comprehensive assessment of our proposed algorithm and its applicability in real-world industrial settings,we curated a line-scan image dataset featuring weld seams.This dataset,named the Standardized Linear Depth Profile(SLDP)dataset,was collected from actual industrial sites where autonomous robots are in operation.Ultimately,we conducted experiments utilizing the SLDP dataset,achieving an average accuracy of 92.7%.Our proposed approach exhibited a remarkable performance improvement over the prior method on the identical dataset.Moreover,we have successfully deployed the proposed algorithm in genuine industrial environments,fulfilling the prerequisites of unmanned robot operations.

Classification of MAG weld pool image based on moment invariants and fisher

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%.

Weld pool image sensor for pulsed MIG welding

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.

Novel welding image processing method based on fractal theory

Computer vision has come into used in the fields of welding process control and automation. In order to improve precision and rapidity of welding image processing, a novel method based on fractal theory has been put forward in this paper. Compared with traditional methods, the image is preliminarily processed in the macroscopic regions then thoroughly analyzed in the microscopic regions in the new method. With which, an image is divided up to some regions according to the different fractal characters of image edge, and the fuzzy regions including image edges are detected out, then image edges are identified with Sobel operator and curved by LSM (Lease Square Method). Since the data to be processed have been decreased and the noise of image has been reduced, it has been testified through experiments that edges of weld seam or weld pool could be recognized correctly and quickly.

Weld pool vision sensing and image processing for GMAW

It is difficult to acquire satisfied weld pool image by CCD sensor during gas metal arc welding（ GMAW） , for arc disturbs violently, welding current is great and working frequency is high. By using CMOS vision sensor to GMA W process, the vivid weld pool image is collected at any time, furthermore, whose gray compression ratio is controllable by sensor hardware circuit developed. Acquired weld pool image is firstly pre-processed by using Wiener filter and Ostu threshold segmentation algorithm. Subsequently separation between weld pool image and cathode mist region is conducted by means of mathematical morphological algorithm, and the edge of weld pool image is extracted by using Prewitt algorithm.

An adaptive thresholding for weld seam image recognition in real time

Image prooessing of wehl seam in real time is an importunity to make welding rohot be able to track weld seam. The algorithm described in this paper combines some image technologies, such as modified Sobel edge detector and Hough transformation function, and especially the thresholds for image processing are ore aled adaptively by Ineans of a neural network. aests proved that this algorithm has a high reliability and rapidity in distinguishing the position of weld seam even with noises. The algorithm can be used ac the basic program .for robot to track welding seam and furthermore for calculating 3 dimensional information plan robot movement automatically.

BACKGROUND RECTIFICATION AND FEATURE EXTRACTION OF IMAGE IN A SPOT WELD OF AL ALLOY X-RAY DETECTION

A primary study on Processing in X - ray inspection of spot weld for aluminum alloy spot welding,in- cluding for background simulation,acquisition of ideal binary image, and extraction and identifi- cation of defect features was presented.

Real-time measurement of welding temperature field and closed loop control of penetration

Colormetric method of images by using two different wavelength images is a new measuring method for welding temperature field on the basis of ordinary colorimetric method, which depends little on the measuring distance, emissivity of body etc. In this paper the real time measuring system and measuring principle of welding temperature field are described, the whole welding temperature field is real time measured, so the temperature distribution at the welding direction and its cross section is obtained, then parameters of thermal cycle. With data from the temperature closed loop control system of the parameters of temperature field is developed and tested. Experimental results prove that it has high measurement speed (time of a field within 0.5 s ) and good dynamic response quality. Weld penetration can be controlled satisfactorily under the variation of welding condition such as welding thickness, welding speed and weldment gap etc.

Modeling the radiometric imaging process of weld pool

In the vision monitoring or controlling the arc welding process, it is a prerequisite to get a clear image of weld pool. However, the disturbance of arc radiation makes imaging of weld pool difficult and optical filters are usually used to improve the image quality. In this paper, a radiometric imaging model is established to investigate the influence of the filter on the image quality of the weld pool, in which the spectral distribution of weld pool radiation, the spectral transmittance of the filter, the spectral sensitivity of the camera are all considered. With the proposed model, the influence of the factors on weld pool imaging can be inferred and the selection of optical filters is discussed.

Development of Welding Multi-Information Remote Wireless Monitoring System Based on STM32

A single sensor is used to obtain welding information in welding monitoring process, but this method has some shortcomings. In order to obtain more comprehensive and reliable welding information, this paper designed and built a welding multi-information wireless monitoring system with STM32-F407ZET6 as the control core and ALK8266 as the wireless transmission module. Real-time acquisition, transmission and display of electric arc signal and welding image information are realized in the monitoring system. This paper mainly introduces the hardware and software core of the monitoring system. At the same time, the signal collected by the monitoring system is compared with the original signal, and the accuracy of the remote monitoring system is tested. The monitoring system is used in welding test. The test results show that the accuracy of the monitoring system meets the requirements, and the on-line monitoring of electric arc signal and welding image can be realized in the welding process.

Modified Gray Level Difference-Based Thresholding Segmentation and its Application in X-Ray Welding Image

Thresholding is a popular image segmentation method that often requires as a preliminary and indis- pensable stage in the computer aided image process, particularly in the analysis of X-ray welding images. In this paper, a modified gray level difference-based transition region extraction and thresholding algorithm is presented for segmentation of the images that have been corrupted by intensity inhomogeneities or noise. Classical gray level difference algorithm is improved by selective output of the result of the maximum or the minimum of the gray level with the pixels in the surrounding, and multi-structuring of neighborhood window is used to represent the essence of transition region. The proposed algorithm could robustly measure the gray level changes, and accurately extract transition region of an image. Comparisons with other approaches demonstrate the superior performance of the proposed algorithm. K

Residual stress determination in friction stir butt welded joints using a digital image correlation-aided slitting technique

This paper presents an incremental cutting method for evaluating the longitudinal residual stresses in a butt welded thin plate via combining the traditional residual stress measurement methods and the advanced optical technique.The proposed approach,which can be called digital image correlation（DIC）-aided slitting technique,introduces a successive extension slot to a specimen and employs the DIC technique to measure the released displacement profiles of the cutting sections after each cutting increment.Then the displacement profiles are used to directly calculate the residual stress distributions up to the slot tip and hence,a stress distribution can be obtained after a cutting increment.Finally,all of the stress distributions are averaged to ultimately determine the original residual stress field.This method does not include any complex experimental operations or tedious derivation,and the resolution of stress variation is greatly improved by the continuous measurement of the released displacements.The presented method has been preliminarily verified by a specimen with residual stress introduced by a four-point bending test.The results show that residual stresses determined by the DIC-aided slitting technique agree well with those from finite element（FE） prediction.The residual stress in a friction stir welded aluminum specimen obtained by the presented technique is also consistent with the evaluations given by X-ray diffraction.Furthermore,the residual stresses obtained by the DIC-aided slitting technique demonstrate higher accuracy and stability than the evaluations derived by the DIC-aided contour method.

Sequential Similarity Detection Algorithm Based on Image Edge Feature

： This paper proposes a new sequential similarity detection algorithm （SSDA）, which can overcome matching error caused by grayscale distortion; meanwhile, time consumption is much less than that of regular algorithms based on image feature. The algorithm adopts Sobel operator to deal with subgraph and template image, and regards the region which has maximum relevance as final result. In order to solve time-consuming problem existing in original algorithm, a coarse-to-fine matching method is put forward. Besides, the location correlation keeps updating and remains the minimum value in the whole scanning process, which can significantly decrease time consumption. Experiments show that the algorithm proposed in this article can not only overcome gray distortion, but also ensure accuracy. Time consumption is at least one time orders of magnitude shorter than that of primal algorithm.