Automatic Welding Process Research Articles

MAFNet: a two-stage multiple attention fusion network for partial-to-partial point cloud registration

Abstract 3D point cloud registration is a critical technology in the fields of visual measurement and robot automation processing. In actual large-scale industrial production, the accuracy of point cloud registration directly affects the quality of automated welding processes. However, most existing methods are confronted with serious challenges such as the failure of partial-to-partial point cloud model registration when facing robot automatic processing guidance and error analysis work. Therefore, this paper proposes a novel two-stage network architecture for point cloud registration, which aims at robot pose adjustment and visual guidance in the field of automated welding by using 3D point cloud data. Specifically, we propose a neighborhood-based multi-head attention module in the coarse registration stage. The neighborhood information of each point can be aggregated through focusing on different weight coefficients of multi-head inputs. Then the spatial structure features which is used to establish the overlapping constraint of point clouds are obtained based on above neighborhood information. In the fine registration stage, we propose the similarity matching removal module based on multiple attention fusion features to explore deeper features from different aspects. By using deep fusion features to guide the similarity calculation, the interference of non-overlapping points is removed to achieve the finer registration. Eventually, we compare and analyze the proposed method with the SOTA ones through several error metrics and overlap estimation experiments based on the ModelNet40 dataset. The test results indicate that our method, relative to other mainstream techniques, achieves lower error rates and the most superior accuracy of 98.61% and recall of 98.37%. To demonstrate the generalization performance of proposed algorithm, extensive experiments on the Stanford 3D Scanning Repository, 7-Scenes and our own scanning dataset using partially overlapping point clouds individually under clean and noisy conditions show the validity and reliability of our proposed registration network.

Exploring the cutting edge: Recent trends in cold metal transfer welding

Cold metal transfer welding is known for its automated welding process, which is equipped with shortcircuit-based deposition of filler wire, which allows it to control its heat input parameter properly along with a wire feed rate. Cold metal transfer’s main characteristic, which greatly affected the manufacturing industries, is joining thin, similar, or dissimilar metal sheets as the processing heat input is minimal. This review paper (covering 104 studies) examines how joining different metals with varying welding parameters affects their weld appearance, microstructure, tensile strength, and the formation of joint failure. The main focus was on what additional methods, like hardfacing or post-heat treatment of material, must be adopted to enhance the joint's weld quality and appearance. The paper starts with the investigation of numerous dissimilar weld joints formed by the cold metal transfer technique, along with the effect of varying welding parameters and ultrasonic-assisted cold metal transfer hybrid welding on the weld quality and post–pre-weld heat treatment of materials. A comparison of different cold metal transfer arc modes employed in wire-arc additive manufacturing has also been discussed briefly. At the end of the analysis, it was noted that some metal joints had a positive impact, and some gained a negative effect while increasing the heat input. The research articles studied in this paper indicate that not every material would exhibit the same welding property when subjected to a specific set of varying welding parameters.

Automatic welding seam tracking and real-world coordinates identification with machine learning method

In the automatic welding process, the precision of the welding position significantly influences welding quality, relying heavily on the accurate identification of the welding seam. However, in complex and unstructured welding environments, such as those with strong arc lights, welding splashes, and thermal-induced deformations, various disturbances present a significant challenge to identify the welding seam. This paper introduces a cost-effective welding seam tracking model constructed using a laser line and a fixed viewpoint single RGB camera. The model's primary objective is to detect a chain of welding-seam points in both captured images and real-time camera feeds. The paper presents the techniques for camera calibration, laser detection, and the use of artificial intelligence to establish a real-world coordinate frame. The process begins with camera calibration using the OpenCV library to filter noise and undistort images. Subsequently, the thresholding technique is employed for color image segmentation, isolating the laser sensor light on the workpiece. An algorithm is then introduced to detect welding spots. Finally, the image coordinates are converted to world coordinates using two machine learning methods: Random Forest Regression and Gradient Boosting Regression. Experimental demonstrations were conducted at different positions on the object to assess algorithm precision. The results indicate average deviations of 0.83 mm, 0.74 mm, and 0.77 mm for X, Y, and Z coordinates, respectively, which fall below the expected standard deviation of 3 mm. Despite the overall consistency of the program, slight noise from environmental lighting may still exist. In conclusion, the proposed welding seam tracking method and coordinate conversion program have proven effective and cost-efficient, with potential for future improvements.

Dynamic robot routing optimization: State–space decomposition for operations research-informed reinforcement learning

There is a growing interest in implementing artificial intelligence for operations research in the industrial environment. While numerous classic operations research solvers ensure optimal solutions, they often struggle with real-time dynamic objectives and environments, such as dynamic routing problems, which require periodic algorithmic recalibration. To deal with dynamic environments, deep reinforcement learning has shown great potential with its capability as a self-learning and optimizing mechanism. However, the real-world applications of reinforcement learning are relatively limited due to lengthy training time and inefficiency in high-dimensional state spaces. In this study, we introduce two methods to enhance reinforcement learning for dynamic routing optimization. The first method involves transferring knowledge from classic operations research solvers to reinforcement learning during training, which accelerates exploration and reduces lengthy training time. The second method uses a state–space decomposer to transform the high-dimensional state space into a low-dimensional latent space, which allows the reinforcement learning agent to learn efficiently in the latent space. Lastly, we demonstrate the applicability of our approach in an industrial application of an automated welding process, where our approach identifies the shortest welding pathway of an industrial robotic arm to weld a set of dynamically changing target nodes, poses and sizes. The suggested method cuts computation time by 25% to 50% compared to classic routing algorithms.

Research on welding seam tracking algorithm for automatic welding process of X-shaped tip of concrete piles using laser distance sensor

AbstractThe manufacturing of the X-shaped tip of prestressed centrifugal concrete piles is nowadays done half automatically by combining the manual worker and the automatic welding robot. To make this welding process full automatically, the welding seam tracking algorithm is considered. There are many types of sensors that can be used to detect the welding seam such as vision sensor, laser vision sensor, arc sensor, or touch sensor. Each type of sensor has its advantages and disadvantages. In this paper, an algorithm for welding seam tracking using laser distance sensor is proposed. Firstly, the fundamental mathematics theory of the algorithm is presented. Next, the positioning table system supports the procedure is designed and manufactured. The object of this research is the fillet joint because of the characteristics of the X-shaped tip of the concrete piles. This paper proposes a new method to determine the welding trajectory of the tip using laser distance sensor. After that, the experimental results are received to verify the proposed idea. Finally, the improved proposal of the algorithm is considered to increase the accuracy of the suggested algorithm.

Machine Learning Algorithm Comparison for the Performance Evaluation of Manual Welding Process

With the development of technology, the shipbuilding industry has seen a rise in automated welding processes. However, manual welding continues to be a necessary and in-demand skill. Unfortunately, the supply of both high-skilled and unskilled welders has steadily declined over the past decade, leading to a shortage of professional manpower. To address the issue of manpower shortage, a proposal has been made to provide timely and efficient training program for unskilled welders. However, evaluating the effectiveness of the training has proven challenging due to the lack of clear criteria for assessing the performance. This paper conducts an effective performance evaluation of unskilled welders using powerful machine learning algorithms. The evaluation is based on a dataset collected from both high-skilled and unskilled welder groups in manual welding processes. A comparison study is conducted to determine the most suitable algorithm. The goal is to identify the positive and negative parameters in the training of the manual welding process and provide an effective education strategy for unskilled welders. Additionally, the paper aims to find the algorithm with the highest accuracy. Overall, this study seeks to provide a solution to the shortage of manual welding professionals through the development of an efficient education strategy.

Prediction of internal welding penetration based on IR thermal image supported by machine vision and ANN-model during automatic robot welding process

Welding quality is a critical criterion for evaluating welding operations. Traditional evaluation methods suffer from drawbacks such as lack of objectivity, untimeliness, and high costs. Therefore, real-time monitoring and assessment of the weld pool have become the mainstream trend in welding technology. This study introduces a novel method for defining weld pool width boundaries. It utilizes an infrared (IR) camera to capture the weld pool temperature clusters and employs the Sobel operator for convolution to generate the gradient map of the weld pool temperature clusters. Through enhanced processing in the gradient map, the width boundaries of the weld pool are more effectively detected compared to previous methods. Previous studies defined weld pool width boundaries by identifying characteristic points with the most distinct temperature fluctuations, caused by the different radiative properties of the same material in different states. However, practical tests revealed susceptibility to interference from reflected arc light. The proposed method mitigates the impact of reflected arc light and is applicable to complex multilayer welding scenarios. To address the lag in quality monitoring, reduce welding costs, and achieve real-time monitoring of the weld pool process, we employed machine vision and an artificial neural network (ANN) model. This led to the development of a weld penetration assessment system based on infrared thermal images. The system successfully predicted the penetration depth for 4 mm carbon steel with an accuracy of 86.6 %. This validates the feasibility of estimating and predicting weld performance using the surface temperature characteristics of the weld pool. The newly proposed weld pool boundary definition method holds promise for real-time monitoring in more complex multilayer pipe welding scenarios. It lays the groundwork for predicting and fusing the weld depth in intricate multi-pass pipe welding.

TENSILE, IMPACT AND NON-DESTRUCTIVE ANALYSIS OF 316 L STAINLESS STEEL FOR MARINE APPLICATIONS

Welding is an age-old method used for joining the metals permanently. The marine industry is a major user of sheet metal components that benefit from custom welded blanks (TWBs). These advantages encompass weight, cost, and noise savings, as well as increases in crash safety, improved efficacy, and oxidation resistance. However, machinability issues are prevalent as a result of the welding process. These benefits and drawbacks are explored, as well as TWB forming techniques, welding procedures, and materials utilized in the marine sector. In this study two different thickness 316L stainless steel grade plate welded using manual and automatic TIG Welding process. The process parameters are chosen for this study is welding current, voltage, welding speed, shielding gas & filler diameter. The manual TIG welded specimen was than compared with automatic TIG welded specimen in terms of Liquid Penetration test, tensile and impact test. The result and discussion are briefly explored.

Aluminum alloy oxidation prediction during laser welding process based on random forest regression analysis of spectral signals

Aluminum alloys are one of the most important materials in modern industries; however, they are susceptible to oxidation during the welding process. In an automated welding process, the online monitoring and prediction of weld bead oxidation degree are particularly important. This study proposes a novel method to real-timely predict the oxidation degree of the aluminum alloy during the laser welding process based on the laser plasma spectral signals. First, the characteristics of laser plasma spectral signals are analyzed under various oxidation degree conditions. And then, a random forest regression model is built to extract the principal characteristic wavelengths of spectral signals and predict the oxidation degree of weld bead based on these spectral signals. Finally, through experiments, the prediction validity of the proposed method is verified.

Design and analysis of robot and fixture pedestal for OTC FD-V8 MAG welding robot

The use of automation in the welding process is favoured due to its capacity to enhance the welding quality and expedite the completion of the task. Welding is a commonly automated process in assembly lines, with many companies relying on robotic welding due to its efficient nature. The key advantages of an automated welding process include higher-quality welds, increased productivity, reduced waste production, and lower labour costs. Gas Metal Arc Welding (GMAW) is of two types: namely, Metal Inert Gas (MIG) welding or Metal Active Gas (MAG) welding. GMAW is a welding process that involves a welding gun through which a wire electrode and a shielding gas are fed continuously. This process is commonly performed using a direct current power source with constant voltage, but other types of power sources can also be used. GMAW offers four primary methods of metal transfer, namely globular, short-circuiting, spray, and pulsed-spray, each of which has its unique properties and benefits as well as limitations. In this study, the OTC FD-V8 model robot is used for welding. The pedestal for the robot is designed using SOLIDWORKS and the static analysis of the robot pedestal is done. The fixture is used to hold the work piece for welding. The quality of the weld bead is determined by parameters like voltage, welding current, wire diameter, and composition of the shielding gas.

Intelligent and Adaptive System for Welding Process Automation in T-Shaped Joints

The automation of welding processes requires the use of automated systems and equipment, in many cases industrial robotic systems, to carry out welding processes that previously required human intervention. Automation in the industry offers numerous advantages, such as increased efficiency and productivity, cost reduction, improved product quality, increased flexibility and safety, and greater adaptability of companies to market changes. The field of welding automation is currently undergoing a period of profound change due to a combination of technological, regulatory, and economic factors worldwide. Nowadays, the most relevant aspect of the welding industry is meeting customer requirements by satisfying their needs. To achieve this, the automation of the welding process through sensors and control algorithms ensures the quality of the parts and prevents errors, such as porosity, unfused areas, deformations, and excessive heat. This paper proposes an intelligent and adaptive system based on the measurement of welding joints using laser scanning and the subsequent analysis of the obtained point cloud to adapt welding trajectories. This study focuses on the optimization of T-joints under specific welding conditions and is intended as an initial implementation of the algorithm, thus establishing a basis to be worked on further for a broader welding application.

Development of automatic orbital pipe MIG welding system and process parameters’ optimization of AISI 1020 mild steel pipe using hybrid artificial neural network and genetic algorithm

Development of automatic orbital pipe MIG welding system and process parameters’ optimization of AISI 1020 mild steel pipe using hybrid artificial neural network and genetic algorithm

Study of the TIG Welding Process of Thin-Walled Components Made of 17-4 PH Steel in the Aspect of Weld Distortion Distribution.

This article presents the results of a study on the distribution of weld distortion in thin-walled components made of 17-4 PH steel, resulting from TIG (Tungsten Inert Gas) welding. Both manual and automatic welding processes were examined. Physical simulation of the automated welding process was conducted on a custom-built welding fixture. Analysis of weld distortion in thin-walled components made of 17-4 PH steel was based on the results of measurements of transverse shrinkage and displacement angle values. These measurements were taken on thin-walled parts before and after the welding process using a coordinate measuring machine (CMM). To determine the effect of manual and automated welding processes on the microstructure of the welded joint area, metallographic tests and hardness measurements were performed. The microstructure was analyzed using a scanning electron microscope (SEM). An analysis of the chemical composition of selected welded joint zones was also conducted. These tests were performed using an optical emission spectrometer (OES). According to the results, the use of automated welding and special fixtures for manufacturing thin-walled aircraft engine components made of 17-4 PH steel reduces the propensity of these components for distortion due to the effects of the thermal cycle of the welding process. This conclusion is supported by the results of the observation of the microstructure and analysis of the chemical composition of the various zones of the welded joint area.

Experimental and Simulation Studies of Micro-Swing Arc Welding Process for X80M Pipeline

Pipe girth welds are prone to incomplete fusion problems in the automatic welding process of long-distance pipelines, which is often related to temperature inhomogeneity in the weld bead. The narrow gap and micro-swing welding technique was applied in pipeline construction to improve welding quality. The manuscript provides a detailed investigation of the micro-swing welding technique with a combination of welding experiments and numerical simulation. A swing welding strategy was proposed according to the actual welding condition in pipeline construction to study the formation mechanism of weld joints. The swing width grew to 1.25–1.35 times from the 3 to 6 o’clock position in the same filling layer. It also increased with filling layers, and filling layer 5 had the biggest swing width, almost two times that of filling layer 2. “Middle concave” morphology appeared at the 3 o’clock position, which could effectively avoid the occurrence of incomplete fusion, while “hump” morphology may appear at the 6 o’clock position, and incomplete fusion defects occurred if the next pass failed to eliminate the influence of the “hump”. The temperature field presented an obvious “sawtooth” shape at small swing frequencies, which could cause temperature inhomogeneity. It could be effectively eliminated when swing frequency reached over 5 Hz.

Study on Microstructure and Properties of P92 Steel Joint with Narrow Gap Automatic Welding

The microstructure and mechanical properties of automatic welding joint of P92 steel are studied by means of optical microscopy and mechanical property testing. The results show that: the welded joint of P92 steel with narrow gap automatic welding has good fusion, and no defects such as unfusion, porosity and slag inclusion are found in the weld metal. The microstructure of weld and HAZ is tempered martensite. The hardness distribution in different areas of the welded joint is uniform, the impact toughness of the weld and HAZ is good, and exceed that of manual welding, the strength of the joint meets the standard requirements, and the residual stress distribution of the whole joint is low. Therefore, P92 steel welded joint obtained by narrow gap automatic welding process has good performance and obvious advantages.

Generation mechanism of lack of fusion in X70 steel welded joint by fully automatic welding under steep slope conditions based on numerical simulation of flow field

X70 pipeline steel is butt welded by fully automatic welding at 25° slope, and the characteristic information of welding process is collected. A 3D transient heat and mass transfer model of weld pool is established. This model was verified by means of the shape of the weld pool and the two-dimensional shape of the weld, and then, the flow field of the fully automatic welding process under steep slope conditions was simulated to clarify the mechanism of the lack of fusion defect. The results show that the welding arc is deflected when it stays on both side walls of the groove. The slope makes the liquid metal tend to gather at the lower groove. When gravity plays a leading role in the flow of the molten pool, some liquid metal begins to flow out from the lower groove to the front end, resulting in an overflow phenomenon. The generation of overflow phenomenon and arc deflection cause the formation of a “void zone” at the structure mutation position in front of the groove. In the welding process, the liquid metal tends to flow to the side walls for heat transfer under various thermal effects, and forms a large range of eddy current at the side walls. This has a positive effect on sidewall melting. In addition, the effect of surface tension at the lower groove is more obvious than that at the upper groove, and the trend of upward flow along the side wall is stronger, so it is difficult for the high-temperature liquid metal in the arc center to flow to the “void area” located at the bottom of the side wall of the lower groove. Therefore, the bottom of the lower groove is more likely to cause lack of fusion defect.

Minimizing occupational risk by automation of the special processes - based on occupational risk assessment

Revolution 4.0 and the resulting changes in process management have a very large impact on the meaning and method of safety management. With the beginning of a new industrial era, it is also necessary to introduce changes in occupational risk assessment. It should be taken into account that economy 4.0, in addition to improving production efficiency, also aims to minimize hazardous factors affecting a human. This paper presents the occupational risk assessment in the position of a welder on the basis of defined hazards. The risk assessment analysis was performed comparatively for manual welding operator and for the operator of an automated welding station. The purpose of the occupational risk assessment was also to identify preventive measures that would minimize the occurrence of risk during the manual welding process, as well as to analyse the impact on the risk after introduction of an automated welding process, and thus eliminating the need to expose the operator to numerous hazardous factors. In the paper it has been shown that many of hazardous factors have a much smaller impact on the level of safety at the employee. Some of the dangerous factors have been almost eliminated. And generally, the introduction of process automation significantly reduces the occupational risk while working in certain professions.

Creep rupture behavior of 2.25Cr1Mo0.25V steel and weld for hydrogenation reactors under different stress levels

Abstract In the present research work, the 2.25Cr1Mo0.25V steel plates with a thickness of 112 mm were welded using the multi-pass submerged automatic arc welding process. The creep specimens were prepared from the base metal (BM) and weld metal (WM) in the welded joint after heat treatment process. The uniaxial creep tests were performed to investigate the creep deformation and rupture behaviors at 550°C under different applied stress levels. The microstructure and fracture surface morphology of crept BM and WM samples were also characterized using the scanning electron microscope with energy-dispersive X-ray spectroscopy. The results showed that typical three-stage creep deformation curves are observed in both BM and WM specimens, and the BM exhibits a faster deformation rate than the WM. Both the creep rupture time and uniaxial creep ductility are found to be increased with a decrease in applied stress. Furthermore, the relationship between the minimum creep rate and time to rupture of both BM and WM samples was obtained, and it can be described using a unified Monkman–Grant equation. In addition, it is found that the creep fractures of the BM and WM are a transgranular ductile failure. The creep damages of both materials are mainly associated with the microstructural degradations, that is, the initiation and coalescence of creep cavities at second phase particles such as carbide and inclusion particles along the loading direction.

Analysis and Optimization of Automatic Argon Arc Welding Process for Thin Wall Parts

Analysis and Optimization of Automatic Argon Arc Welding Process for Thin Wall Parts

Parameter monitoring and control of the friction stir welding process

A control algorithm and the implementation example of a corresponding control system for a friction welding machine designed for experimental work on the friction stir welding technology of large-sized products from aluminum alloys are described. Brief characteristics of the experimental-industrial installation «Malachite» are given. A method to control the welding mode for the process automation according to the main drive power is found. The emergency events separation for automatic friction stir welding is introduced. The application of optical communication between equipment for mode control and unification of panel solutions for friction stir welding is tested. Keywords friction stir welding, aluminum alloys, welded assemblies from aluminum alloys, welding process automation, pure welding technologies, optical communication