Automatic Welding System Research Articles

Weld seam object detection system based on the fusion of 2D images and 3D point clouds using interpretable neural networks

This study introduces a novel approach that addresses the limitations of existing methods by integrating 2D image processing with 3D point cloud analysis, enhanced by interpretable neural networks. Unlike traditional methods that rely on either 2D or 3D data alone, our approach leverages the complementary strengths of both data types to improve detection accuracy in environments adversely affected by welding spatter and smoke. Our system employs an improved Faster R-CNN model with a ResNet50 backbone for 2D image analysis, coupled with an innovative orthogonal plane intersection line extraction algorithm for 3D point cloud processing. By incorporating explainable components such as visualizable feature maps and a transparent region proposal network, we address the “black box” issue common in deep learning models.This architecture enables a more transparent decision-making process, providing technicians with necessary insights to understand and trust the system’s outputs. The Faster-RCNN structure is designed to break down the object detection process into distinct, understandable steps, from initial feature extraction to final bounding box refinement. This fusion of 2D-3D data analysis and interpretability not only improves detection performance but also sets a new standard for transparency and reliability in automated welding systems, facilitating wider adoption in industrial applications.

Robotic welding system for adaptive process control in gas metal arc welding

Changing process conditions such as distortion, varying seam preparation or gap width during welding is a major challenge in automated gas metal arc welding (GMAW). While human welders can adjust the process during welding (e.g. welding speed, torch orientation), an automated welding system needs sensors to detect and actuators to adjust the process. Adjusting the process in response to changing process conditions is usually referred to as adaptive welding. The aim of this work is to build a robotic welding system capable of automatically adapting the welding process using some of the approaches of a human welder. To enable adaptive process control, a robotic welding system is built. It consists of four main components: a six-axis industrial robot for mechanical guidance of the welding torch, a welding power source, a monochrome visual camera as an image sensor and a process controller that combines the three components. The camera captures images of the weld pool during welding and processes the images to provide geometrical information such as the width of the weld pool and the position of the weld pool front. Changes in the weld pool geometry are quantified, and an adjustment strategy is generated in the process control unit in real time. Process adjustments can be mechanical (e.g. welding speed, torch orientation) and electrical by adjusting synergic process settings (wire feed speed, arc length, process dynamics). Validation tests demonstrate the functionality of the welding system. Two use cases were investigated. Firstly, a deposited weld bead was examined, and variations in the width of the weld pool were induced by varying the welding speed. The second application was a seam tracking application. The path is pre-programmed, and the specimen is positioned with an offset to the path. Compensation for the offset is implemented.

Health assessment of welding by-products in a linear welding automation: Temperature and smoke concentration measurements

Due to its potential to improve production and weld quality, automated welding systems are growing in popularity in industrial applications. However, these technologies generate potentially dangerous by-products like welding gases and fumes. By evaluating the temperature range and smoke concentration near the welding area, this study intends to assess the health parameters of welding by-products in linear welding automation. A four-wheeled robot system equipped with joint detection and referencing technologies will be the research subject, which will also improve welding conditions to match industrial standards. Also, the study will look into how welding factors affect smoke concentration and temperature range. The findings of this study will shed light on the health risks posed by automated welding systems and guide the creation of safety regulations that will shield workers from hazardous consequences.

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

Development of Automatic Gantry MIG Welding System

Development of Automatic Gantry MIG Welding System

A Study on the Efficiency Evaluation for the Motion Parameters of the Manual Welding Process Using Data Envelopment Analysis

The shipbuilding industry has applied automatic welding systems to increase productivity as well as address the shortage of skilled welder. However, a manual labor is still required in welding process where automatic systems cannot be applied. Since the past decade, the number of skilled welders in the shipbuilding industry has been continuously decreasing. Accordingly, various education equipment and systems have been developed for the manual welding process in order to increase education efficiency and reduction of training time . However, when educating trainees, the educational equipment and systems prioritize parameters such as current, voltage, gas flow, and wire speed. In contrast, ergonomic parameters such as hand tremor and posture are neglected as minor factors . Therefore, in this study, we analyzed the skilled welders and trainees and compared them to increase education efficiency. To conduct this study, we utilized analysis methods based on data envelopment (DEA) and statistics . DEA can evaluate the relative efficiency between decision making units (DMUs) and derive improvement way based on the efficiency ratios. The proposed method can derive the improvement way of each trainee among ergonomic parameters based on the experimental outcome from the DEA.

Real-time segmentation network for accurate weld detection in large weldments

Aiming at the defects of inaccurate weld extraction and high matching error rate in automatic welding system of large weldments currently. We propose a multi task detection model based on CNN architecture, which integrates the semantic segmentation technology required for weldment merging as well as the edge detection technology needed for weld matching. In particular, for the purpose of predicting smoother edges and welds, we carefully construct a new segment head, which adopts the sub-pixel convolution technology for up-sampling. Furthermore, a joint optimization loss function is explored to alleviate the imbalance of category distribution in large-scale weldment datasets. To verify the effectiveness of the model, abundant groups of data are collected for training and testing. The experimental results indicate that the proposed method has achieved the optimal trade-off between detection accuracy (83.35% mIoU, 95.15% F-score of welds and edges) as well as speed (74FPS) on a 2080Ti GPU compared with other state-of-the-arts, which greatly improves the robustness of the automatic welding system for large weldments.

Research and development of weld tracking system based on laser vision

Aiming at the shortcomings of low real-time, low applicability, and low welding precision of automatic welding system, a seam tracking system based on laser vision is designed. Use the laser vision sensor to collect the weld image and transmits it to the industrial control computer for processing. Using a median filter to eliminate noise impacts such as arc and splash. Then, this paper focuses on the combination of an improved image threshold segmentation algorithm is used to solve the optimal threshold to obtain the binary image. And the information of laser stripe and the background are separated, overcomes the problems that the researchers have encountered before, such as the unrecognized global optimal solution, and the inaccuracy of the segmentation caused by system jitter. Finally, combined with the improved upper and lower average method, least square method, and Hough transform, the weld feature points are identified and more ideal real-time weld tracking is realized. The experimental results show that the method can accurately track the weld feature points, and improve the detection speed.

Application of Intelligent Technology on Tunnel Steel Structure Factory

At present, the construction of tunnel steel structure factories has been common, but most of them are still on the low end. In addition, the manual processing modes face certain problems, such as high waste rate, low efficiency, and discrete welding of steel components. To address these problems, this paper introduces an intelligent management cloud platform, aiming to realize unmanned control methods and construct an intelligent tunnel steel component processing plant. There are four main production lines in the intelligent steel structure factory. First, an intelligent production line of a tunnel grille arch effectively improves the production efficiency, production quality, and dust removal effect of the grille arch through the automatic welding technology of a reinforcement mechanism-based welding robot. Second, a processing line of a steel pipe for tunnel construction improves the overall processing efficiency, saves costs, and reduces work intensity by using an intelligent numerical control system, a pneumatic clamping device, a plasma cutting hole assembly, and a 360-degree automatic rotation system. Third, an automatic feeding platform of section steel arch production line adopts the six-axis robot sensor clamping connecting plate positioning and six-axis robot sensing three-plane automatic welding system, which not only compensates for the defects of manual production but also realizes the reduction, increases efficiency, and improves welding quality and precision. Fourth, an automatic steel mesh production line saves much labor and enhances site management and production efficiency through vertical and horizontal reinforcement pay-off racks. Overall, in this study, the construction goals of informatization, intellectualization, and personnel downsizing of the tunnel steel structure processing have been achieved.

Crack Elimination and Surface Quality Enhancement of the Wear-resistant Layer on Guide Slippers of Coal Cutting Machines

In order to enhance the surface quality and avoid the cracking problem of the wear-resistant layer on guide slippers of coal cutting machines, an automatic welding system was employed for the overlaying welding production. By regulating the welding parameters, including the welding path and speed, the surface flatness and quality were greatly reduced. The cracks at the arc extinguishing positions were effectively eliminated. As compared to the conventional manual welding, the automatic welding not only reduced the machining allowance, but also increased the production rate and the service life of the guide slippers.

An Insight into the Scope of Implementation of Intelligent Welding in Welding of Titanium

Traditionally welding is considered as an art rather than a science. The quality of the weld is dependent on the skill and intuition of the welder. The welding process is mostly not reliable and labor-intensive. The solution to the problems in welding lies in utilizing intelligent welding techniques where in the selection of weld parameters like voltage, current, speed etc and defect control is done intelligently by the automated welding system. The intelligent welding system shall comprise elements, viz., control system, sensing, design and modeling of process and application of artificial intelligence. The application of intelligent welding system has developed into a new field of automation called as ‘Integrated Computational Welding Engineering (ICWE)’. The welding of titanium and its alloys is predominantly dependent on the skill of the welder. Majority of research and industrial practice is based on the traditional manual welding process and hence it is prone to defects deterioration of metallurgical, mechanical and corrosion properties. There is scope in adopting ICWE in welding of titanium and its alloys.

Open-Closed-Loop Iterative Learning Control with the System Correction Term for the Human Soft Tissue Welding Robot in Medicine

By combining manual welders (with intelligence and versatility) and automatic welding systems (with accuracy and consistency), an intelligent welding system for human soft tissue welding can be developed in medicine. This paper presents a data-correction control approach to human welder intelligence, which can be used to control the automated human soft tissue welding process. Human soft tissue welding can preconnect the excised tissue, and the shape of the tissue at the junction ensures the recovery of the operative organ function. This welding technology has the advantages of rapid operation, minimal tissue damage, no need for suture materials, faster recovery of the mechanism and properties of the living tissue, and the maintenance of the function of the organs. Model of the welding system is identified from the data; an open-closed-loop iterative learning control algorithm is then proposed to improve the tracking accuracy of the system. The algorithm uses the tracking error of current and previous to update the control law. Meanwhile, to further improve the accuracy under the conditions of external interference, a system correction term is added to the proposed ILC algorithm, which can be adjusted according to the system’s errors and output and improve the capability of the target tracking greatly. A detailed convergence analysis for the ILC law has been given. Simulation results verify the feasibility and effectiveness of the proposed method for GTAW control tasks.

Multiple weld seam extraction from RGB-depth images for automatic robotic welding via point cloud registration

Robotic welding technology is constantly growing with the development of vision technologies. To establish a fully automatic robotic welding system, an automated weld seam extraction process with accurate perception of the target workpiece (i.e., object) is one of the most challenging tasks. Although many methods pertaining to automatic weld seam extraction have been proposed, most of the previous studies are difficult to employ in practical systems because the algorithms are unable to simultaneously handle multiple and occluded seams from arbitrary view directions. In this study, we propose a novel method to extract weld seams based on point cloud registration from various view directions that can handle randomly occluded seams in a workpiece with multiple seam parts. We focus on the shape of the weld seams as a line or curve, which are dominant structures in the field. Initially, we extract all detectable weld seams for each image with a single view direction obtained using an RGB-depth vision sensor. Subsequently, three-dimensional points of weld seams obtained from each view direction are filtered based on the edge cues from RGB images. Finally, the extracted weld seams obtained from the various view directions are merged by employing a point cloud registration technique. The experimental results demonstrate that the proposed method outperforms a state-of-the-art method in terms of detection accuracy. Our proposed algorithm can be employed for dynamic workpiece scenes, which indicates that multiple weld seams can be successfully extracted from arbitrary view directions containing scene occlusions.

Improving the algorithm for selecting welding mode parameters under the impact of boundary conditions of the workpiece

This article discusses the application of a mathematical model of heat transfer during welding to create an algorithm for choosing the welding mode parameters during programming of automatic welding systems. The results of the industrial implementation of a robotic welding system equipped with a developed algorithm for choosing a welding mode are presented.

Development of an Automatic Welding System for the Boiler Tube Walls Weld Overlay

Tube walls are an essential part of the thermal power plant boiler. During the operation of the boiler, the heating surface of the tube walls are exposed to furnace particles, intense heat, and chemical components resulting from the combustion reaction. These cause corrosion and wear, which permanently collapse the tubes, and affect the reliability and performance of the boiler. Therefore, a protection layer of heat and corrosion-resistant material is typically welded on the surface of the tube walls. In this study, a dedicated weld overlay automatic system is proposed. The downward welding technique with the pulse gas metal arc welding (GMAW) process is used to accomplish the proposed approach. The system generates and plans beads sequence based on the analysis of the tube walls geometry. The inverse kinematic theory was used to calculate the coordinates and transformations of the welding torch. Then, a mathematical model for the welding torch trajectory was established. A SIMOTION controller was adapted for motion control. A weld-tracking system based on the adaptive neuro-fuzzy inference system (ANFIS) was used to solve the welding distortion and the assembly error. The experiment results show that the proposed design is efficient and reliable compared to previous methods. The degree of automation and the weld overlay quality of the boiler tube walls have been notably improved.

Advanced Automatic Welding System for Offshore Pipeline System with Seam Tracking Function

Automatic welding technology is a solution to increase welding productivity and improve welding quality in offshore pipe welding. To increase welding productivity, it is necessary to save time during the assembly/disassembly of the guide track from the welding carriage and pipe to move the next station. The guide track consists of a pneumatic system that does not separate the welding carriage, and two welding carriages operate on a half-pipe joint to increase productivity. These welding carriages automatically operate under the controller command. An automatic welding system consists of a DC motor module, a step motor module, a welding control module, a welding monitoring module, and a central control module. The control systems incorporate control modules and transmit commands to each module for an automatic welding system. In order to minimize the inevitable misalignment between the centerline of the welding seam and the welding torch for each welding pass, a moving average algorithm for seam tracking is proposed, which was proven to be suitable for the root pass, filling pass, and cap pass. Welding experiments were also carried out to verify the validity of the weld seam tracking system.

Prediction Model for Back-Bead Monitoring During Gas Metal Arc Welding Using Supervised Deep Learning

Creating and consistently maintaining the weld shape during gas metal arc welding (GMAW) is vital for ensuring and maintaining the specified weld quality. However, the back-bead is often not uniformly generated owing to the change that occurs in the narrow gap between the base metals during butt joint GMAW, which substantially influences weldability. Automating the GMAW process requires the capability of real-time weld quality monitoring and diagnosis. In this study, we developed a convolutional neural network-based back-bead prediction model. Specifically, scalogram feature image data were acquired by performing Morlet wavelet transform on the welding current measured in the short-circuit transform mode of the GMAW process. The acquired scalogram feature image data were then analyzed and used to develop labeled weld quality training data for the convolutional neural network model. The model predictions were compared with welding data acquired through additional experiments to validate the proposed prediction model. The prediction accuracy was approximately 93.5%, indicating that the findings of this study could serve as a foundation for the future development of automated welding systems.

An Image-Processing Method for Extracting Kinematic Characteristics of Droplets during Pulsed GMAW

Pulsed gas metal arc welding (GMAW) is widely applied in industrial manufacturing. The use of pulsed GMAW was found superior to the traditional direct-current (DC) welding method with respect to spatter, welding performance, and adaptability of all-position welding. These features are closely related to the special pulsed projected metal transfer process. In this paper, a monitoring system based on a high-speed camera and laser backlight is proposed. High-quality images with clear droplets and a translucent arc can be obtained at the same time. Furthermore, a novel image-processing algorithm is proposed in this paper, which was successfully applied to remove the interference of the arc. As a result, the edge and region of droplets were precisely extracted, which is not possible using only the threshold method. Based on the algorithm, centroid coordinates of undetached and detached droplets can be calculated, and more parameters of the kinematic characteristics of droplets can be derived, such as velocity, acceleration, external force, and momentum. The proposed monitoring system and image-processing algorithm give a simple and feasible way to investigate kinematic characteristics, which can provide a new method for possible applications in studying mathematic descriptions of droplet flight trajectory and developing a precise automatic welding system.

A Study on Global and Cluster-wise Regression Model in the Automatic GMA welding

The automatic welding system is presently made use of high volume production industries even if the cost of the related equipment is justified by the large number of pieces to be made. Also, the detailed movement devices with the predetermined sequences of welding parameter and the use of timers to form the weld joints were required. A new mathematical model that predict the optimal welding parameters on a given bead geometry and accomplish the desired mechanical properties of the weldment to make the automatic GMA (Gas Metal Arc) welding process should be needed. The developed model should be employed a wide range of material thicknesses and be applicable for all welding positions as well. In addition, the algorithm must be available in the form of mathematical equations which can be programmed easily to the robot and give a high degree of confidence in predicting the bead dimensions. In this study, two regression models with global regression and cluster-wise regression are proposed to be applicable for prediction of optimal welding parameters on the bead reinforcement area. For development of the proposed regression models, an attempt has been done for applying to a several methods. A series experiments to research the effects of welding parameters on bead reinforcement area as a function of key output parameters for the lab-joint weld in the automatic GMA welding process was performed. Not only the fitting of these models was checked and compared by using a variance test (ANOVA), but also the prediction of bead reinforcement area using the developed regression models were carried out the basis of the additional experiments.

Automatic welding system design for transformer station grounding steel based on PLC

Based on the analysis of the type of grounded flat steel welding, the transformer station grounding flat steel automatic welding system is designed by using the XDM PLC as the main controller, and the three-axis motionmechanism and the R-axis rotationmechanism as actuators. According to working requirements, such as four-dimensional space degree of freedom welding requirements, system hardware configurations, the actuator design, system hardware selection, and the hardware connection form of the system are determined at first. The paper introduces the composition and working principle of the automatic welding system, focusing on the coordinate transformation relationship in the visual measurement, and gives the calibration process. The compensationmethods after the rotation of the welding torch at each inflection point are discussed, and the different welding parameters are used according to different seam types during the welding process. The flow chart of control program is given out for the welding gun attitudes adjustment. The testing welding result shows this designed system can track the welding seam quite well and welding quality is satisfying, the more, this system can improve the welding efficiency greatly.