Tungsten Electrode Abrasion Length Detection Based on Semantic Segmentation and Tip Restoration

Electron beam melting (EBM) is a powder bed additive manufacturing (AM) technology for small and medium-sized Ti-6Al-4V components. In this study, EBM-built Ti-6Al-4V tensile specimens were joined using tungsten inert gas (TIG) welding and laser beam welding (LBW) to form large-scale components. Weld morphology, defects, mechanical properties, and microstructure of joints made by LBW and TIG welding were compared. It was found that the pore sensitivity of EBMed Ti-6Al-4V is extremely high. In EBM, the most common defect is pores, but this has been ignored as parts are broken at welding zone. Large pores are distributed along the edge of the weld in TIG welding, whereas in laser welding they are distributed at top of the weld. LBW has a much smaller grain size in the weld center than TIG welding. The TIG welded sample has more heat at the weld boundary. Mechanical properties of TIG welded parts were superior to laser welded parts. The main reason for this is that the weld cross section is larger than the center. In addition, in the microstructure examination of TIG welding, it was observed that the weld had fewer defects than laser welding. Also, the elongation of all specimens is very low.

A very thin, needlelike electrode can be formed at the tip of thin tungsten electrode by a single discharge with rather high discharge current. We have demonstrated some practical applicability of such very thin electrode. Understanding the formation mechanism of such electrodes is an important issue to utilize the phenomenon to practical applications. We should see what happens on the electrode during the discharge. In this study, the change of electrode shape at tip part of a thin metal electrode induced by single discharge with a large current was observed dynamically by a stroboscopic imaging system with high time resolution. In the imaging system, the second harmonics of a Q-switched neodyum: yttrium-aluminum-garnet laser is used for lighting of charge-coupled device camera and it can take a photo with time resolution of about 10ns. Electrode materials were tungsten and copper of 100μm diameter and the discharge current was 30A with 400μs duration. Both the positive and negative polarities of electrodes in machining oil as well as in air were examined using steel work piece. Rather drastic move of melt formed by the discharge occurred after discharge in all cases. Observed images reveal that the electrode tip part after single discharge is in a molten state and the melt part moves upwards after the end of the discharge, and final electrode shape is formed at about 1ms after the discharge. The thin, needlelike form of tungsten electrode is found to be the residue of unmelted portion of the electrode left after the move of melted part. Tungsten electrode becomes the needlelike shape when the thin electrode has negative polarity. When the polarity is reversed, or copper electrodes are used, the tips of the electrodes become spherical forms. For copper electrode with negative polarity in air and at some specific time, droplets of molten metal are suspended in the space between the electrode and the work piece.

An Analysis of the Mechanical Behavior of AISI 4130 Steel after TIG and Laser Welding Process

Information provided in this article can be used for estimating the radiation dose associated with the use of thoriated tungsten electrodes in tungsten inert gas welding. Area and breathing zone concentrations of 232Th generated by welding and electrode sharpening along with particle size information; isotopic composition of electrodes from two domestic manufacturers and one European manufacturer; and process variables and estimates on the number of thoriated tungsten electrodes manufactured are presented. Past literature is reviewed and compared with the results of this study. Isotopic analysis of a nominal 2% thoriated electrode found 0.6 ppm +/- 0.4 ppm 230Th and less than 0.1 ppm 228Th. Analysis of a ceriated tungsten electrode and a lanthanated tungsten electrode for 232Th found 124 ppm and 177 ppm, respectively. Electrode consumption during welding was primarily the result of tip sharpening. Less than 3% of the weight loss was attributable to the welding process. The in-mask concentration of respirable thorium particulate in the welder's breathing zone was 0.002 x 10(-12) microCi 232Th/mL. The concentration of respirable thorium particulate from electrode sharpening was 1.3 x 10(-12) microCi 232Th/mL. The measured sharpening time was 20 sec per electrode. Estimates of the activity median aerodynamic diameters for the respirable fraction of the welding and electrode sharpening aerosols were 3.5 and 5 microns, respectively, when measured in the breathing zone at 0.3 m (12 inches) from the point of operation. The respirable fraction of the total welding and sharpening aerosols was 45 and 60%.

Welded stainless steel components used in power plants and chemical industries are subjected to mechanical load cycles at elevated temperatures which result in early fatigue failures. The presence of weld makes the component to be liable to failure in view of residual stresses at the weld region or in the neighboring heat affected zone apart from weld defects. Austenitic stainless steels are often welded using Tungsten Inert Gas (TIG) process. In case of single pass welding, there is a reduced weld penetration which results in a low depth-to-width ratio of weld bead). If the number of passes is increased (Multi-Pass TIG welding), it results in weld distortion and subsequent residual stress generation. The activated flux TIG welding, a variant of TIG welding developed by E.O. Paton Institute, is found to reduce the limitation of conventional TIG welding, resulting in a higher depth of penetration using a single pass, reduced weld distortion and higher welding speeds. This paper presents the fatigue crack growth rate characteristics at 823 K temperature in type 316LN stainless steel plates joined by conventional multi-pass TIG (MP-TIG) and Activated TIG (A-TIG) welding process. Fatigue tests were conducted to characterize the crack growth rates of base metal, HAZ and Weld Metal for A-TIG and MP-TIG configurations. Micro structural evaluation of 316LN base metal suggests a primary austenite phase, whereas, A-TIG weld joints show an equiaxed grain distribution along the weld center and complete penetration during welding (Fig. 1). MP-TIG microstructure shows a highly inhomogeneous microstructure, with grain orientation changing along the interface of each pass. This results in tortuous crack growth in case of MP-TIG welded specimens. Scanning electron microscopy studies have helped to better understand the fatigue crack propagation modes during high temperature testing.

Grain fragmentation in ultrasonic-assisted TIG weld of pure aluminum

Gas tungsten arc welding (GTAW) is a widely used method of joining aluminium and its alloys. Despite the fact that a lot of research has been done in this area for several decades, there are many unresolved issues on the welding process control. Optimization of square wave alternating current profiles is one of them. This paper presents the results of studies on control of spatial position of an arc by an improved heat input algorithm taking into account the necessary relationship between direct current of straight and reverse polarity. It is shown that an increase in direct current reverse polarity to over 10 A contributes to expansion of a cathode spots space and, consequently, a greater deviation of the arc from the axis of a tungsten electrode. The spatial position of the arc is almost coaxial to the tungsten electrode when direct current reverse polarity is short-term reduced to 5 A at the final stage. These results are correct for a wide range of the square wave alternating current profiles.

The tungsten inert gas (TIG) welding process is widely used in various industries for its ability to produce high-quality welds at a low cost. However, TIG welding struggles with welding thick stainless steel in a single pass, reducing production efficiency. To address this, new TIG variants such as activated TIG (A-TIG), flux bound TIG (FB-TIG), and flux zone TIG (FZ-TIG) have been developed to enhance penetration in austenitic stainless steel. This study investigates the effects of TiO2 and Fe2O3 flux on 304 stainless steels welded using A-TIG, FB-TIG, and FZ-TIG processes. Results show a slight increase in the depth-to-width (d/w) ratio for A-TIG and FB-TIG, while FZ-TIG achieved a 59% higher d/w ratio compared to autogenous TIG welding. The increased penetration is attributed to the reversal Marangoni convection and arc constriction. Microstructural analysis reveals a higher delta ferrite content in A-TIG and FZ-TIG welds due to increased heat input. Additionally, FZ-TIG welds exhibited an 11.5% higher microhardness compared to autogenous TIG welds. FZ-TIG welding enhances penetration and mechanical properties effectively.

Study on microstructure and mechanical properties of 304 stainless steel joints by TIG, laser and laser -TIG hybrid welding

Sampling and Analysis of Welding Fumes and Gases Produced Under Experimental Hyperbaric Conditions

GTAW welding (gas tungsten arc welding) or commonly called TIG (tungsten inert gas) welding is welding using a flame arc produced by a fixed electrode made of tungsten. One thing that needs to be considered in welding (especially in TIG welding) is the effect of welding amperage on the mechanical properties or strength of the welded joint. PeThe tests carried out in this study were tensile tests and micro tests. Tensile tests were carried out with the aim of knowing the tensile strength of the test specimens. And the micro test is carried out aiming to see the microstructure that occurs in the weld area (HAZ). Data analysis was carried out by looking at the relationship of tensile stress, yield stress, and strain that occurred in the test specimen based on variations or parameters used during welding. Based on the analysis of the mechanical properties and microstructure of thematerial stainless steel sus 304 musing TIG welding (Tungsten Inert Gas)with a current variation of 80 A, 100 A and 120 A showed a difference that caused a comparison of the difference in the tensile strength. Welding using a current of 80 A has the highest average stress of 316.6 kN/mm2, welding using a current of 100 A has a tensile strength of 378.6 kN/mm2. While welding using a current of 120 A has the highest tensile strength of 458.3 kN/mm2. The results of this test indicate that the analysis of the mechanical properties and microstructure of TIG welding (Tungsten Inert Gas) shows a significant effect of tensile strength at a current of 120 A, so it has the highest tensile strength with an average value of 458.3 kN/mm2

04/00550 SLLV phase behavior and phase diagram transitions in asymmetric hydrocarbon fluids: Shaw, J. M. and Béhar, E. Fluid Phase Equilibria, 2003, 209, (2), 185–206.

This study tackles the challenges of inconsistent weld quality and limited real-time monitoring in Tungsten Inert Gas (TIG) welding by developing a digital twin for the process. The primary objective is to enhance process efficiency and quality control by creating a high-fidelity virtual model of TIG welding that enables real-time monitoring and control. To achieve this, the study employs Desirability Function Analysis (DFA) to optimize multiple quality characteristics. The methodology integrates advanced sensors and IoT technologies to gather real-time data on critical welding parameters such as current, voltage, travel speed, and gas flow rate. This data is used to create a simulation model that accurately replicates the physical welding process. The experiments are conducted using digital twin on SS304 thin which is widely used in industrial applications. By applying DFA, the study converts multiple quality characteristics into a single composite desirability score, offering a quantitative assessment of process efficiency and output quality. The experimental results demonstrate the digital twin’s ability to accurately predict and control welding outcomes, significantly improving productivity and quality control. This research highlights the transformative potential of digital twin technology in TIG welding, paving the way for smarter, data-driven decision-making in industrial settings.

In this study, we propose a segmentation model based on convolutional neural networks (CNNs) to address image segmentation challenges in computer vision. Prior to designing the model, the activation function and other modules of the convolutional neural network were optimized to meet specific requirements. The segmentation task was transformed into binary classification problem to simplify network calculations and improve efficiency. Additionally, the model utilized a mask map obtained from the semantic segmentation model to aid in instance segmentation. Class activation technology was introduced to extract feature mapping maps. The corresponding thermal maps were obtained to achieve target instance segmentation. To further validate the effectiveness of the segmentation model, simulation experiments were conducted on semantic segmentation and instance segmentation respectively. The results show that the accuracy of the basic semantic segmentation model reached 87.58%, while the average accuracy of the entire class of the optimized instance segmentation model reached 97.9%. Therefore, the research and design of image segmentation models demonstrate high accuracy and good robustness.

Mechanical and corrosion properties of TIG welded dissimilar AISI 420 and UNS S32205 stainless steel sheets