Control Of Welding Process Research Articles

Survey on artificial intelligence (AI) applied in welding: A future scenario of the influence of AI on technological, economic, educational and social changes

The application of artificial intelligence (AI) in the field of welding is an increasingly important area of research and a large number of journal publications on the topic have been published. A keyword search for AI in welding in the leading scientific journal databases Elsevier and Springer reveals more than 3,000 related articles. The large publication volume shows the importance being attributed to AI in welding and the breadth of the contributions of researchers utilizing AI approaches to tackle challenges and problems in welding. Such challenges include poorly controlled welding parameters and weld geometry, which lead to weld quality problems. This paper reviews previous studies on AI systems utilized in welding process control and welding robot control. Case studies on the utilization and development of AI systems in the Finnish welding industry are also presented. Analyses of the findings provide the means to predict future scenarios for a 5–10 year time frame on the impact of AI in the welding industry in the era of Industry 4.0. The changes that AI bring will drive a need for new technological, economic and social policies as well as reform of educational curricula and skills training in the sphere of sustainability and quality of life. Consideration of trends and scenarios is important for both academia and industry, where new research ideas and developmental trends on AI systems will emerge for practical implementation.

Multi-sensor Data Fusion for Online Quality Assurance in Flash Welding

Abstract The flash welding process is a mainstream to manufacture anchor chains in the shipbuilding industry. However, traditional quality control approaches only use the tension test of the whole chain. This cannot adequately guarantee the quality of each anchor chain. Also, the incurred cost of post-build repair is far more than production. There is an urgent need to design and develop new quality control methods for real-time monitoring and control of flash welding processes. In this investigation, we firstly develop a data acquisition and control system to collect sensor data pertinent to process dynamics (i.e., electrode-position and electric-current profiles) and monitor the flash welding process in real time. Then a novel spatiotemporal warping approach is proposed to quantify the dissimilarity of electric-current and electrode-position signals collected in the flash welding process. Further, we embed the resulted warping matrix into feature vectors in the low-dimensional space that preserves the dissimilarity distances. Finally, Dirichlet Process (DP) models are proposed to cluster embedded features (coordinates in low-dimensional space). Experimental results demonstrated that the proposed methodology not only effectively reveals the directional differences among flash welding profiles, but also significantly outperforms traditional clustering algorithms such as the K-means approach, i.e., 13.25%, 1.67% and 12.33% increases in the prediction performance with the use of electric-current, electrode-position and combination recordings, respectively.

An Automatic Detection and Identification Method of Welded Joints Based on Deep Neural Network

Welding quality is an important factor to affect the performance, quality and strength of different products, and it will affect the safe production. Therefore, welding quality detection is a key process of industrial production. And the detection and identification of welded joints are the premise of welding quality detection, which could reduce the quality detection range and improve the detection precision. Welded joint identification is also important for providing information for automatic control of welding process. Faced with the complex characteristics of industrial environment, such as weak texture, weak contrast and corrosion, we propose a detection and identification method of welded joints based on deep neural network. Firstly, aimed at the problem of insufficient training samples, combined with image processing and Generative Adversarial Network (GAN), the high-quality training samples are generated. Secondly, the updating mechanism of training samples is established to guarantee that the deep neural network model could cover all samples. Finally, the detection and identification of welded joints are realized by the deep neural network which could avoid the handcrafted features of conventional machine learning methods. Experiments show that the proposed method could quickly and efficiently finish the detection and identification task of welded joints. Meanwhile, the proposed method could well solve the detection and identification problems of complex industrial environment.

An intelligent weld control strategy based on reinforcement learning approach

Welding process control is an important part to realize intelligent welding. The actual welding process is a complex and nonlinear system influenced by multiple factors, such as welding current, arc voltage, welding speed, and so on. In addition, welding process is always interfered by working conditions, which make the reliability of general control model reduce greatly. So an intelligent weld control strategy that based on actor-critic reinforcement learning (ACRL) approach is selected to control the width of weld pool. And the gas tungsten arc welding (GTAW) and gas metal arc welding (GMAW) models are used to conduct simulation experiments of welding process control to verify the feasibility of the controller preliminarily. Finally, the opened-loop control experiment and the closed-loop control experiment are done, and the results are compared to verify the reliability of the controller.

Control of Droplet Detachment Frequency in a GMAW Process by a Hybrid Model Predictive Control

Efficient control of a gas metal arc welding (GMAW) process enables one to obtain high quality products as a consequence of achieving a high quality weld. Although control of the droplet detachment frequency in the welding process would play a great role in improving the welding quality, measuring this variable is difficult and expensive. In this paper, we attempt to control the frequency of droplet detachments without directly measuring it. To this end, we utilize the hybrid property of the GMAW process to indirectly control the frequency. Specifically, a mixed logical dynamical (MLD) model is obtained by considering the hybrid act of the process during droplet detachment. Then, a nonlinear model predictive controller with variable control and prediction horizons is designed incorporating the hybrid behavior of the process. The controller regulates the droplet detachment frequency without measuring this variable directly. Computer simulation results show that the proposed controller leads to a higher quality weld compared to the present approaches.

Towards robust sequential ultrasonic spot welding of thermoplastic composites: Welding process control strategy for consistent weld quality

The research in this paper is an essential part of a bigger effort on developing robust sequential ultrasonic welding of multi-spot welded joints in thermoplastic composites. It mainly focused on assessing the impact of the changes in boundary conditions on the welding process and whether it could be circumvented by using an appropriate process control strategy. A two-step approach was followed by investigating: (1) the effect of boundary conditions on displacement- and energy-controlled single-spot welded joints and (2) displacement- and energy-controlled sequential ultrasonic welding of double-spot welded joints. The results showed that previous spots indeed affect the energy required to obtain an optimum new welded spot, which challenges the use of energy-controlled welding for this application. Contrarily, displacement-controlled welding was shown to provide consistent-quality welds with a constant set of welding parameters and it was hence identified as the most promising welding strategy for sequential ultrasonic welding of thermoplastic composites.

Weld bead recognition using laser vision with model-based classification

Abstract Weld bead recognition is important for providing information for automatic control of welding process and also for post-weld inspection. Bead geometry profiles can be measured by a laser-line profile sensor projecting a laser line onto the welding surface and receiving the reflection to calculate the height of the surface. As the bead is usually very small, it may be easily covered by the sensor noise or distorted by the bending of the work pieces after welding. In addition, it is difficult to estimate the parameters of bead width and bead height while moving the laser sensor to cover a 3D surface, since the movement may cause unstable measurements. This work investigates using a model-based classification method to automatically segment the bead from the welding surface regardless of the distance and the angle of the scanner to the welding surface. It firstly uses a polynomial model together with the Expectation-Maximisation (EM) algorithm fitting into the distance profiles measured by the laser sensor, and then automatically removes the surface curvature. Consequently the shape of the bead can be easily extracted from the welding surface by applying a small value of threshold depending on the noise level of the data. Experimental results show that the Butt welding bead parameters of bead width and height can be extracted successfully. The method is robust to the bending of the welding surface and the unstable movement of the laser sensor.

Output characteristic and arc length control of pulsed gas metal arc welding process

A pulsed gas metal arc welding (P-GMAW) power source is produced with a stepped output characteristic. The steeped output characteristic control circuit is designed based on peak current-mode control and one cycle control methods An adaptive arc length control method is put forward and introduced based on a digital signal controller (DSC). Bead-on-plate experiments are carried out on mild steel to investigate the influences of output characteristics on the stability of P-GMAW process in an open-loop arc length control condition.Results show that stepped characteristic at background duration has the advantage of decreasing arc extinguishments and short-circuits phenomena, and the welding process is more stable without spatters than constant current or constant voltage characteristic. Welding with adaptive arc length control strategy, the dynamic behavior of arc working point and arc length is described, resulting in an identical arc length at the end of background time for each pulse period. One-drop-per-pulse transfer mode is obtained by carefully selecting pulse parameters with a droplet radius approximately equal to that of the electrode. Arc lengths are measured with different threshold voltages and background currents. The mathematical model of threshold voltage with respect to arc length and welding current is established through multiple linear regression analysis method. Welding with a step wire-feed speed and a step CTWD, the adaptive arc length control strategy shows strong disturbance resisting ability.

Optimization of resistance welding by using electric servo actuator

The paper is focused on the control of resistance projection welding process applied in joining of thin-walled metal elements. The motion of electrode is generated by electric servo actuator that controls the force exerted on electrode or alternatively, just travel itself of electrode. The projection welding has been discussed for welding of 1.5 mm thick DX53 steel sheets where one sheet contains an embossed projection. Apart of electric servo actuator, another source of force has been described, i.e. pneumatic actuator (classical one), for the reason of comparison. The solution where the electric servo operates together with appropriate algorithm makes the new solution that is alternative for classical, pneumatic one. Optimized motion of electrode due to new proposed source of electrode force or/and travel, based on relevant algorithm yields improved quality of joints.

Parametric Optimization of Gas Metal Arc Welding Process by using Taguchi method on Ferritic Stainless Steel AISI409

Welding process parameters can plays a very significant role in determining the quality of the welded joint in metal inert gas (MIG) welding operation. The elaborated experiments and analysis have been needed to precise control of the MIG welding process to obtain the desired quality characteristics in welded specimens. Present work is planned to study and analyze the effects of welding parameters: welding current, gas flow rate and nozzle to plate distance, on ultimate tensile strength (UTS) and percentage elongation (PE) in MIG welding of AISI409 ferritic stainless steel materials. Experiments have been conducted as per L9 orthogonal array of Taguchi method. The visual inspection and X-ray radiographic test has also been conducted in order to detect surface and sub-surface defects of welded specimens. The observed data of UTS and PE have been interpreted, discussed and analyzed with use of Taguchi methodology and analysis of signal to noise ratio. Some conclusive remarks have been drawn from the study.

Automated control of the laser welding process of heart valve scaffolds

Abstract Using the electrospinning process the geometry of a heart valve is not replicable by just one manufacturing process. To produce heart valve scaffolds the heart valve leaflets and the vessel have to be produced in separated spinning processes. For the final product of a heart valve they have to be mated afterwards. In this work an already existing three-axes laser was enhanced to laser weld those scaffolds. The automation control software is based on the robot operating system (ROS). The mechatronically control is done by an Arduino Mega. A graphical user interface (GUI) is written with Python and Kivy.

Technology of Ultrasonic Control Of Gas-Shielded Welding Process

A new approach to implementation of electrode metal transfer control under MAG, MIG welding is suggested. The process ensures control of thermal and crystallization processes, stabilizes the time of electrode metal drop formation. The results of the research allow formulating the basic criteria of electrode metal transfer control via ultrasonic exposure, determining the conditions of producing a more equilibrium structure of deposit metal.

Modeling and robust controlling of laser welding process on high strength titanium alloy using fuzzy basis function networks and robust Takagi-Sugeno fuzzy controller

The purpose of this paper is to present and implement a novel approach to data-driven modeling and robust control of a laser keyhole welding process. The objective is to maintain the penetration depth of the laser welding process at a desired value under system uncertainties. A framework was proposed to estimate the keyhole diameter and the keyhole penetration depth in real time by type-1 and type-2 fuzzy basis function networks, and an adaptive divided difference filter. A robust Takagi-Sugeno fuzzy controller was implemented to adjust the laser power of the welding process. Experimental results demonstrated that the fuzzy models provided an accurate estimation of both the welding geometry and its variations due to uncertainties, and the robust Takagi-Sugeno fuzzy controller successfully reduced the penetration depth variation and improved the quality of the welding process.

Possibilities for Application of Friction Stir Welding Process to Titanium TiGr2

The interest in friction stir welding (FSW) of different categories of light metallic materials, including titanium and its alloys, has growing in recent years.Due to favorable ratio between strength and density, titanium and its alloys have increasingly used in applications in priority areas (e.g. aeronautics and in aerospace). Having the best impact strength and good corrosion resistance, these materials find applications in chemistry, nuclear and military technology.This paper present the results obtained at friction stir butt welding of TiGr2 sheets with thickness 4mm.The experimental program has developed using three categories of welding tools: with smooth cylindrical pin and flat shoulder, with tapered pin and flat shoulder, respectively with tapered pin having four plane chamfers and flat shoulder. The welding experiments have made using combinations of tools and welding parameters.The control of FSW welding process of titanium TiGr2 sheets has done using an innovative method namely infrared thermography technique.The research program has focused on development of some welding tools and welding regimes correlated with obtaining some of better mechanical characteristics for welded joints.Results obtained to the friction stir butt welding of titanium TiGr2, lead to conclusion that welding joints without defects and with good mechanical characteristics can be obtained, if are known and met the specific requests regarding applying of FSW process to this type of material.

Welding seam profiling techniques based on active vision sensing for intelligent robotic welding

Intelligent robotic welding involves replicating the role of a manual professional welder to adaptively control the welding process. This is necessary to achieve accurate, fast and high-quality welding process in addition to the challenging factors for humans to operate in the welding environment. Therefore, robotic welding exists since the early days of robotics and it is still an active research area. This is why there have been numerous researches in this area for a very long time. Among various techniques proposed by researchers for the adaptive control of the robotic welding process, vision-based control is the most popular due to its non-invasiveness. Therefore, in this paper, we review, analyse and categorise the proposed vision-based techniques with the aim of covering the different image processing and feature extraction aspect of the techniques. The focus is mainly on the active vision system where various image processing techniques have been utilised in extracting the welding seam features. The challenges and difficulties to extract seam features in active vision system have been highlighted. The trends and new approaches have been indicated in order to provide a comprehensive source for researchers who are planning to carry out research related to the intelligent robot vision techniques for welding automation.

Technology of ultrasonic control of gas-shielded welding process

A new approach to implementation of electrode metal transfer control under MAG, MIG welding is suggested. The process ensures control of thermal and crystallization processes, stabilizes the time of electrode metal drop formation. The results of the research allow formulating the basic criteria of electrode metal transfer control via ultrasonic exposure, determining the conditions of producing a more equilibrium structure of deposit metal.

Modeling and Control of Pulsed Double-electrode MIG Welding Process

Pulsed double-electrode metal inert gas welding is a new kind of low heat input welding method. With different connection, parts of welding current bypassed and it controlled the base metal current and melting current separately. With free-flight metal transfer process, it could weld dissimilar metals. Aiming at the unstability of coupling arc in pulsed double-electrode metal inert gas welding process, a dynamic mathematic model has been built to truly describe and simulate the welding process with equivalent simplification, linearization and iterative solution. Then a control scheme is put forward and simulated, which changes the wire feed speed to adjust the main arc length, and further to control the stability of the coupling arc. Also the welding experiments with control scheme are carried based rapid prototyping system. Simulations proved the effectiveness of control scheme. And with controlling, the welding experiment is more stable and a good Al-Fe joint is acquired.

Laser Welding Process – A Review of Keyhole Welding Modelling

Laser welding is used in several industrial applications. It can be distinguished between conduction mode and keyhole mode welding, between pulsed wave and cw laser welding and between CO2-lasers with a wavelength of 10μm and various laser types of about 1μm wavelength. A deeper understanding of laser welding allows improving weld quality, process control and process efficiency. It requires a complementary combination of precise modelling and experimental investigations. The here presented review focuses on modelling of laser keyhole welding, for both wavelength regimes. First, the fundamentals of the laser welding process and its physics such as beam propagation, keyhole formation and melt pool dynamics are addressed. The main approaches for modeling energy transfer from laser beam to keyhole surface as well as fluid flow in the material are then discussed. The most relevant publications are systematically structured, particularly categorized with regard to the respective physical phenomena addressed. Finally some open questions are underlined.

Ultrahigh Vacuum Technologies Developed for a Large Aluminum Accelerator Vacuum System

A large particle accelerator requires an ultrahigh vacuum (UHV) system of average pressure under <TEX>$1{\times}10^{-7}$</TEX> Pa for mitigating the impact of beam scattering from the residual gas molecules. The surface inside the beam ducts should be controlled with an extremely low thermal outgassing rate under <TEX>$1{\times}10^{-9}Pa{\cdot}m^3/(s{\cdot}m^2)$</TEX> for the sake of the insufficient pumping speed. To fulfil the requirements, the aluminum alloys were adopted as the materials of the beam ducts for large accelerator that thanks to the good features of higher thermal conductivity, non-radioactivity, non-magnetism, precise machining capability, et al. To put the aluminum into the large accelerator vacuum systems, several key technologies have been developed will be introduced. The concepts contain the precise computer numerical control (CNC) machining process for the large aluminum ducts and parts in pure alcohol and in an oil-free environment, surface cleaning with ozonized water, stringent welding process control manually or automatically to form a large sector of aluminum ducts, ex-situ baking process to reach UHV and sealed for transportation and installation, UHV pumping with the sputtering ion pumps and the non-evaporable getters (NEG), et al. The developed UHV technologies have been applied to the 3 GeV Taiwan Photon Source (TPS) and revealed good results as the expectation. The problems of leakage encountered during the assembling were most associated with the vacuum baking which result in the consequent trouble shootings and more times of baking. Then the installation of the well-sealed UHV systems is recommended.

Modeling, simulation and control of pulsed DE-GMA welding process for joining of aluminum to steel

Joining of aluminum to steel has attracted significant attention from the welding research community, automotive and rail transportation industries. Many current welding methods have been developed and applied, however, they can not precisely control the heat input to work-piece, they are high costs, low efficiency and consist lots of complex welding devices, and the generated intermetallic compound layer in weld bead interface is thicker. A novel pulsed double electrode gas metal arc welding(Pulsed DE-GMAW) method is developed. To achieve a stable welding process for joining of aluminum to steel, a mathematical model of coupled arc is established, and a new control scheme that uses the average feedback arc voltage of main loop to adjust the wire feed speed to control coupled arc length is proposed and developed. Then, the impulse control simulation of coupled arc length, wire feed speed and wire extension is conducted to demonstrate the mathematical model and predict the stability of welding process by changing the distance of contact tip to work-piece(CTWD). To prove the proposed PSO based PID control scheme’s feasibility, the rapid prototyping experimental system is setup and the bead-on-plate control experiments are conducted to join aluminum to steel. The impulse control simulation shows that the established model can accurately represent the variation of coupled arc length, wire feed speed and the average main arc voltage when the welding process is disturbed, and the developed controller has a faster response and adjustment, only runs about 0.1 s. The captured electric signals show the main arc voltage gradually closes to the supposed arc voltage by adjusting the wire feed speed in 0.8 s. The obtained typical current waveform demonstrates that the main current can be reduced by controlling the bypass current under maintaining a relative large total current. The control experiment proves the accuracy of proposed model and feasibility of new control scheme further. The beautiful and smooth weld beads are also obtained by this method. Pulsed DE-GMAW can thus be considered as an alternative method for low cost, high efficiency joining of aluminum to steel.